© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 13396
    Prev
    Next
    INDEX
    Explanations

    statistical terms and metrics related to analysis and data representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mariée
    -0.38
     stuk
    -0.36
    ReusableCell
    -0.35
    enumi
    -0.34
     NSCoder
    -0.31
    emptions
    -0.31
    ピース
    -0.31
    AntiForgeryToken
    -0.31
     bibir
    -0.31
     koš
    -0.29
    POSITIVE LOGITS
     confidence
    1.19
     Confidence
    1.09
    Confidence
    1.02
    confidence
    1.00
     CI
    0.90
     interval
    0.88
     intervals
    0.84
    CI
    0.82
     conf
    0.82
    置信
    0.79
    Activations Density 1.088%

    No Known Activations