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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5219
    Prev
    Next
    INDEX
    Explanations

    elements of a programming or scripting language syntax

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

    data structures or memory-related syntax in code, specifically looking at patterns in complex data representations like indexing and memory addressing.

    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
     فريبيس
    -0.48
    AnchorTagHelper
    -0.47
    invokeLater
    -0.45
     للمعارف
    -0.44
     ferons
    -0.43
    InputTagHelper
    -0.42
     &___
    -0.42
    mergeFrom
    -0.40
    Clik
    -0.40
     chofe
    -0.40
    POSITIVE LOGITS
    iNdEx
    0.46
    pidou
    0.41
     point
    0.40
    =$((
    0.38
    AccessFile
    0.35
    PullParser
    0.35
    CharacterOffset
    0.34
     TextAppearance
    0.34
    yntaxException
    0.34
     index
    0.34
    Activations Density 0.366%

    No Known Activations