© 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-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 114984
    Prev
    Next
    INDEX
    Explanations

    terms associated with specific types of groups or collections, particularly in the context of mules or caravans

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

    caravan or carcass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Estados
    -0.40
    ckeye
    -0.36
    AxisAlignment
    -0.34
    ]";
    -0.34
    !";
    -0.34
    }");
    -0.33
    )";
    -0.33
     Butte
    -0.33
     صفحۀ
    -0.33
     Tae
    -0.33
    POSITIVE LOGITS
     caravan
    2.11
     Caravan
    2.02
     caravans
    1.87
     carav
    1.58
     Carav
    1.34
    avan
    0.87
     Caval
    0.69
    Personendaten
    0.69
     nahilalakip
    0.68
    AVAN
    0.66
    Activations Density 0.001%

    No Known Activations