© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 6508
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements, particularly those associated with database queries and programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.64
    PerformLayout
    -0.59
    RefNanny
    -0.58
    endregion
    -0.56
     الحره
    -0.56
    awtextra
    -0.56
    basicConfig
    -0.56
    __*/
    -0.52
    省市镇
    -0.50
     Numerade
    -0.50
    POSITIVE LOGITS
    enumi
    0.54
    findpost
    0.50
    pexpr
    0.43
    aarrggbb
    0.40
    Sinopse
    0.39
    PageRoute
    0.38
     tabPage
    0.37
    脚注の使い方
    0.35
    enumii
    0.35
     detalladas
    0.34
    Activations Density 0.612%

    No Known Activations