© 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. 16024
    Prev
    Next
    INDEX
    Explanations

    database-related terms and structure definitions

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

    data type declarations and field specifications in code (particularly in database schemas, ORM definitions, and type definitions).

    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
    BeginInit
    -0.53
    帖最后由
    -0.52
    ImageContext
    -0.50
     Wicidata
    -0.43
     Infórmanos
    -0.41
    iglio
    -0.38
    RTLI
    -0.38
    bergen
    -0.38
    OGND
    -0.37
    addGroup
    -0.37
    POSITIVE LOGITS
    parsedMessage
    0.59
     nullable
    0.57
    Externé
    0.46
     default
    0.46
     null
    0.42
    ConstraintLayout
    0.42
    charpe
    0.41
    nullable
    0.41
     ProtoMessage
    0.41
    execSQL
    0.40
    Activations Density 0.064%

    No Known Activations