Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10081
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "query" in relation to database operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -0.93
     Pingback
    -0.88
     Cæsar
    -0.87
     ་་
    -0.86
     myſelf
    -0.84
     itſelf
    -0.84
     Majefty
    -0.82
     whoſe
    -0.81
     Anſ
    -0.81
     Reſ
    -0.80
    POSITIVE LOGITS
    query
    1.64
     query
    0.84
    SequentialGroup
    0.82
    QUERY
    0.69
    UpInside
    0.67
    Query
    0.66
    migrationBuilder
    0.60
     Query
    0.58
    akas
    0.56
    ViewHolder
    0.56
    Activations Density 0.056%

    No Known Activations