Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15906
    Prev
    Next
    INDEX
    Explanations

    concepts related to supernatural themes and the struggle between good and evil

    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-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
    IntoConstraints
    -0.69
    AntiForgeryToken
    -0.67
     NSCoder
    -0.57
     تضيفلها
    -0.55
    complexContent
    -0.55
    ########.
    -0.53
    findpost
    -0.52
     otomatig
    -0.49
    MigrationBuilder
    -0.48
    URBANA
    -0.47
    POSITIVE LOGITS
     angel
    0.41
     angels
    0.38
     Taktlose
    0.38
    mahl
    0.33
     Angel
    0.33
    entity
    0.33
    новниш
    0.33
    haikusbot
    0.32
    AppMethodBeat
    0.32
    ayuda
    0.32
    Activations Density 0.473%

    No Known Activations