© 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. 38-GEMMASCOPE-RES-16K
    11. 9995
    Prev
    Next
    INDEX
    Explanations

    mentions and references to various "J" entities or prefixes in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.69
    Parcelize
    -0.62
    хьтан
    -0.54
     judgment
    -0.54
     judged
    -0.52
    OGND
    -0.51
    IsMutable
    -0.51
     jasa
    -0.51
     initComponents
    -0.51
    ScopeManager
    -0.49
    POSITIVE LOGITS
    tison
    0.46
     }{@
    0.41
    teenth
    0.41
     ParseException
    0.38
    esterday
    0.38
    tifications
    0.38
    wohl
    0.38
    peño
    0.37
    oneph
    0.36
     schließlich
    0.36
    Activations Density 0.820%

    No Known Activations