© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 17432
    Prev
    Next
    INDEX
    Explanations

    This neuron is effectively inactive — it does not respond to any tokens (always outputs zero).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    expandindo
    -0.46
     propOrder
    -0.41
    wendungs
    -0.37
    ensement
    -0.37
     OFDb
    -0.36
    IntoConstraints
    -0.35
    featureID
    -0.35
     linkovi
    -0.34
    ?”.
    -0.34
    ofür
    -0.34
    POSITIVE LOGITS
    EndInit
    0.72
    ⓧ
    0.68
     disambiguazione
    0.62
     autorytatywna
    0.62
    Hentet
    0.56
    nloa
    0.56
    KURZBESCHREIBUNG
    0.52
     intptr
    0.49
    ########.
    0.47
     дописавши
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.