© 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. 5548
    Prev
    Next
    INDEX
    Explanations

    references to explosive events or accidents

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

    descriptions of violent impacts, collisions, explosions, and physical destruction.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    violent or forceful physical impacts and explosions.

    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
     dedo
    -0.38
     sẵn
    -0.37
    weilen
    -0.37
    pstead
    -0.37
     begegnen
    -0.35
     vœ
    -0.35
     lápiz
    -0.35
     sürekli
    -0.35
     آفت
    -0.34
    cargador
    -0.34
    POSITIVE LOGITS
     shattered
    0.82
     shattering
    0.79
     shatter
    0.69
     fragments
    0.69
     debris
    0.68
     smashed
    0.67
     shards
    0.67
     splin
    0.65
     wreckage
    0.65
     explosion
    0.65
    Activations Density 0.336%

    No Known Activations