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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5284
    Prev
    Next
    INDEX
    Explanations

    modal verbs expressing ability or possibility

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

    the first-person pronoun "I" followed by modal verbs expressing ability or possibility (like "can", "could", "'t").

    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
    ]]>
    -0.31
    vint
    -0.27
     alent
    -0.27
    ///</
    -0.27
     हुए
    -0.26
     }}}{
    -0.26
    **
    -0.25
    </th>
    -0.25
     taba
    -0.25
     Fc
    -0.25
    POSITIVE LOGITS
    :✨
    0.69
    Personensuche
    0.68
    новништво
    0.68
    CloseOperation
    0.62
    protoimpl
    0.62
    sizeCache
    0.61
    principalColumn
    0.60
    sarung
    0.60
    ThroughAttribute
    0.57
    errHandler
    0.56
    Activations Density 0.139%

    No Known Activations