© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 8970
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tag elements and related coding syntax

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

    HTML/XML closing tags and template syntax with angle brackets.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.66
    httphttps
    -0.66
    endphp
    -0.66
     مشين
    -0.57
    SerializedName
    -0.56
    LookAnd
    -0.55
     noqa
    -0.53
    󠁿
    -0.52
    rxjs
    -0.51
     TType
    -0.51
    POSITIVE LOGITS
     jspb
    0.42
    MigrationBuilder
    0.40
    exitRule
    0.36
    Personendaten
    0.33
     stål
    0.32
     AspNetCore
    0.32
    WindowConstants
    0.31
     dever
    0.31
    VPWR
    0.31
    Bakgrunnsstoff
    0.31
    Activations Density 1.610%

    No Known Activations