© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1693
    Prev
    Next
    INDEX
    Explanations

    references to significant events or impacts related to society and technology

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

    substantive nouns and noun phrases that are central topics or concepts in the text.

    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
     StatelessWidget
    -0.74
     ब्रेकडाउन
    -0.73
    hoeddwyd
    -0.73
    twimg
    -0.72
    TagMode
    -0.71
    AddHtmlAttribute
    -0.71
     disambiguazione
    -0.70
    ValueStyle
    -0.69
    kháu
    -0.69
    featureID
    -0.65
    POSITIVE LOGITS
     scares
    0.58
     wasn
    0.58
     weren
    0.52
    ?
    0.51
     sucks
    0.50
    นี่
    0.50
     I
    0.50
     was
    0.49
     stinks
    0.49
     didn
    0.48
    Activations Density 0.392%

    No Known Activations