© 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. 10415
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting cues within text

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

    asterisks or bullet points used as section dividers or markers in formatted 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
    Preparazione
    -0.47
     straff
    -0.41
    )"),
    -0.40
     pinulongan
    -0.39
    }")
    
    -0.36
     infrastruktur
    -0.36
    legungen
    -0.35
    >):
    -0.35
    Lesen
    -0.35
    SqlClient
    -0.34
    POSITIVE LOGITS
    //*
    0.84
    !*
    0.77
    ***********
    0.76
    _*
    0.76
    ****************
    0.76
     *
    0.76
    ?*
    0.76
    :*
    0.75
    -*
    0.74
     (*
    0.73
    Activations Density 0.821%

    No Known Activations