© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 1858
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly quotation marks and periods, suggesting it is focusing on dialogue or conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wol
    -0.71
    яза
    -0.69
     strdup
    -0.68
    inq
    -0.66
    vastava
    -0.65
     Sait
    -0.64
    quec
    -0.64
     getApplication
    -0.63
     IEnumerable
    -0.63
    funcion
    -0.63
    POSITIVE LOGITS
     <=",
    1.30
    MigrationBuilder
    1.10
    ?”
    1.10
    ?"
    1.03
    ,”
    1.00
     مشين
    0.96
    “…”
    0.95
    ":[{
    0.93
    findpost
    0.91
    ,’”
    0.91
    Activations Density 0.104%

    No Known Activations