© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2920
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structures in code

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

    C++ programming code constructs, particularly related to vectors, templates, and standard library syntax.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     nakalista
    -0.61
    tvguidetime
    -0.58
    transQ
    -0.58
    WriteTagHelper
    -0.54
    AnimationsModule
    -0.53
    :✨
    -0.53
    enumi
    -0.53
     simplifié
    -0.53
    makeConstraints
    -0.53
     AssemblyCulture
    -0.53
    POSITIVE LOGITS
     storage
    0.42
     contents
    0.40
     data
    0.40
     memory
    0.39
     collection
    0.38
     dataset
    0.37
     zbior
    0.37
     player
    0.36
     repository
    0.36
     representation
    0.35
    Activations Density 0.164%

    No Known Activations