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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 53757
    Prev
    Next
    INDEX
    Explanations

    references to academic achievements and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    MigrationBuilder
    -0.39
    株
    -0.38
     pinulongan
    -0.38
    жень
    -0.38
    adaptiveStyles
    -0.37
     dAtA
    -0.37
     Biôgrafia
    -0.36
     defaultstate
    -0.36
     mancher
    -0.36
    Obrázky
    -0.36
    POSITIVE LOGITS
     colleague
    0.49
    참고
    0.45
     lecture
    0.43
     betweenstory
    0.42
     colleagues
    0.42
     translating
    0.42
    mitos
    0.42
     postdoctoral
    0.41
    Eloquent
    0.40
     Lecture
    0.40
    Activations Density 0.012%

    No Known Activations