© 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. 15985
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and concepts related to statistical estimation and hypothesis testing

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

    mathematical expressions containing integral notation and variable subscripts/superscripts.

    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
    aarrggbb
    -0.67
    المكان
    -0.64
    SequentialGroup
    -0.60
     Italijani
    -0.57
     صوتيه
    -0.48
    Morfo
    -0.45
    حياتها
    -0.45
    setParent
    -0.44
    حياته
    -0.43
    ItemBackground
    -0.43
    POSITIVE LOGITS
    ViewImports
    0.54
     asti
    0.45
     Vikipedi
    0.43
    igshid
    0.43
    interopRequire
    0.43
    rimp
    0.42
    quíni
    0.42
    bomb
    0.41
    matter
    0.41
     ţ
    0.41
    Activations Density 5.485%

    No Known Activations