© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13716
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structural elements in code snippets

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

    Mathematical expressions and numbers

    np_acts-logits-general · gemini-2.0-flash

    mathematical or code-related text snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xymatrix
    -0.39
     подо
    -0.36
     remarks
    -0.33
    inSlope
    -0.32
    getSubject
    -0.32
    vermögen
    -0.32
     remark
    -0.31
    getLatitude
    -0.31
     amy
    -0.31
     Wikimédia
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.61
     disambiguazione
    0.61
    IntoConstraints
    0.57
    AutoField
    0.53
     HasFactory
    0.53
    requireNonNull
    0.52
     Meksiku
    0.50
    ArgsConstructor
    0.50
     ujednoznacz
    0.49
     gyhoeddwyd
    0.49
    Activations Density 0.655%

    No Known Activations