© 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. 31-GEMMASCOPE-RES-16K
    11. 15158
    Prev
    Next
    INDEX
    Explanations

    specific terms related to biological and genomic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    punctuation marks and special characters used in scientific and technical writing.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.54
    raisemb
    -0.42
    Aiheesta
    -0.42
    𝐗
    -0.40
    RenderAtEndOf
    -0.39
    kuuta
    -0.38
    PYX
    -0.38
    aksikan
    -0.37
     snippetHide
    -0.37
     Febrero
    -0.36
    POSITIVE LOGITS
     visited
    0.67
    dijk
    0.62
     shortest
    0.62
     distance
    0.61
     cost
    0.60
    Cost
    0.59
     explored
    0.59
     Distance
    0.54
     Dijkstra
    0.54
     Cost
    0.54
    Activations Density 0.187%

    No Known Activations