© 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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16067
    Prev
    Next
    INDEX
    Explanations

    names and significant nouns related to identity and relational contexts

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

    This neuron appears to be finding word fragments and character sequences that are unrelated to meaningful content, suggesting it's picking up on noise, encoding artifacts, or OCR errors in the text.

    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
    存于互联网档案馆
    -0.84
     ब्रेकडाउन
    -0.80
    Vidite
    -0.77
     disambiguazione
    -0.76
     <>",
    -0.73
    ロウィン
    -0.73
    MigrationBuilder
    -0.72
    IntoConstraints
    -0.72
    참고
    -0.71
    IUrlHelper
    -0.71
    POSITIVE LOGITS
    istream
    0.29
    woff
    0.26
     bcm
    0.26
     (!(
    0.25
     bien
    0.24
     fol
    0.24
     обе
    0.24
     tal
    0.23
     angeb
    0.23
     necessities
    0.22
    Activations Density 0.753%

    No Known Activations