© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 82268
    Prev
    Next
    INDEX
    Explanations

    mentions of the Angular framework and its components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    NewUrlParser
    -0.46
     Italijani
    -0.42
     sítio
    -0.40
    diğinde
    -0.38
    ställning
    -0.38
     verdaderos
    -0.35
    __":
    -0.35
     chaude
    -0.35
    excellents
    -0.35
    Références
    -0.34
    POSITIVE LOGITS
    DockStyle
    0.78
     فريبيس
    0.55
    PreAuthorize
    0.53
    lapsingToolbar
    0.53
    AddHtmlAttribute
    0.52
    makeText
    0.52
    ğraf
    0.48
    عرِّف
    0.48
     useParams
    0.48
    ExtendWith
    0.48
    Activations Density 0.000%

    No Known Activations