© 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. 15-GEMMASCOPE-RES-16K
    11. 1332
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and copyright language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ктория
    -0.49
    aut
    -0.48
     बेह
    -0.47
    хта
    -0.47
    rouvez
    -0.47
    \}^{
    -0.46
     mantend
    -0.46
    WindowConstants
    -0.45
    ld
    -0.45
     Drittan
    -0.44
    POSITIVE LOGITS
    addCriterion
    6.19
     ModelExpression
    1.10
    ValueStyle
    1.07
    migrationBuilder
    1.05
    awtextra
    1.05
     &___
    0.89
    styleType
    0.84
    Kaynakça
    0.82
    exitRule
    0.80
    WireFormatLite
    0.77
    Activations Density 0.007%

    No Known Activations