© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6393
    Prev
    Next
    INDEX
    Explanations

    programming-related function calls and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming language constructs, particularly related to object method calls and property descriptors.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    code patterns of API/property access and function calls, especially dot- or underscore-delimited identifiers in programming snippets.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    method calls or property accesses using dot notation in code, particularly after class names or object references.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.46
     nonUne
    -0.42
    localctx
    -0.39
    transQ
    -0.38
    BeforeMethod
    -0.37
     invitaciones
    -0.36
     HasFactory
    -0.36
    ExtendWith
    -0.36
     Autorizaciones
    -0.36
    hdashline
    -0.35
    POSITIVE LOGITS
    BorderFactory
    0.67
    copyOf
    0.62
    readAs
    0.58
    fjspx
    0.58
    ChildScrollView
    0.56
    ographically
    0.56
    apnews
    0.56
    OwnProperty
    0.55
     EdgeInsets
    0.55
    :+:
    0.55
    Activations Density 0.159%

    No Known Activations