© 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. 9-GEMMASCOPE-RES-16K
    11. 12790
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data loading and processing in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.42
    endsection
    -0.40
    ientras
    -0.40
     accro
    -0.40
     ayuntamiento
    -0.37
    ngOnInit
    -0.37
     Califor
    -0.37
     auroit
    -0.36
    TintMode
    -0.36
     Niem
    -0.36
    POSITIVE LOGITS
    tagHelperRunner
    0.56
    simd
    0.49
     xmm
    0.49
    windowFixed
    0.46
    usermodel
    0.46
    __*/
    0.45
    quiao
    0.43
    cipes
    0.42
     BorderRadius
    0.40
    prefetch
    0.40
    Activations Density 0.340%

    No Known Activations