© 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. 31-GEMMASCOPE-RES-16K
    11. 15974
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scripting and programming execution

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

    numerical values and quantities in technical contexts.

    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
    usercontent
    -0.41
     nahilalakip
    -0.40
    enumi
    -0.37
    ioutil
    -0.35
     findViewById
    -0.35
    findpost
    -0.35
    FXML
    -0.34
    GHI
    -0.32
    enumii
    -0.32
    featureID
    -0.32
    POSITIVE LOGITS
     running
    2.50
     Running
    2.17
    running
    2.11
    Running
    2.09
     run
    2.03
     RUNNING
    1.98
     runs
    1.86
    运行
    1.82
    RUNNING
    1.76
    run
    1.63
    Activations Density 0.626%

    No Known Activations