© 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. 16010
    Prev
    Next
    INDEX
    Explanations

    percentages and proportions related to various subjects or datasets

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

    percentage expressions followed by descriptions of populations or quantities.

    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
     partly
    -0.45
     partially
    -0.43
    partly
    -0.42
     mostly
    -0.42
    various
    -0.38
    exact
    -0.38
     Audiodateien
    -0.38
    躇
    -0.37
     largely
    -0.37
    mostly
    -0.37
    POSITIVE LOGITS
     total
    0.73
    AndroidJUnit
    0.64
     befolk
    0.64
     totale
    0.63
     revenues
    0.60
     ProtoMessage
    0.60
     respondents
    0.58
     deaths
    0.58
     totales
    0.58
     calories
    0.57
    Activations Density 0.503%

    No Known Activations