© 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. 37-GEMMASCOPE-RES-16K
    11. 8282
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical or engineering processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strix
    -0.43
    Slf
    -0.35
    лтемелер
    -0.34
    Rated
    -0.34
    ysław
    -0.33
     ramo
    -0.33
     répertoire
    -0.33
    EndContext
    -0.33
    DebuggerStep
    -0.33
     Escal
    -0.32
    POSITIVE LOGITS
     alignment
    2.36
     Alignment
    2.09
     aligning
    1.99
     align
    1.95
     alignments
    1.95
     ALIGN
    1.89
    Alignment
    1.88
     Align
    1.86
    alignment
    1.85
     aligned
    1.85
    Activations Density 0.732%

    No Known Activations