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. 122730
    Prev
    Next
    INDEX
    Explanations

    structural features and defects in physical or conceptual frameworks

    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
     Navy
    -0.48
     NgModule
    -0.46
    addLast
    -0.46
     officially
    -0.44
    exp
    -0.44
     navy
    -0.43
     military
    -0.42
     Exp
    -0.41
     exp
    -0.41
    Exp
    -0.41
    POSITIVE LOGITS
     fissure
    0.61
     Gaps
    0.61
     gaps
    0.60
    RenderAtEndOf
    0.60
    隙
    0.60
    IntoConstraints
    0.59
    ]")]
    0.59
     gap
    0.58
    隙間
    0.58
     fissures
    0.57
    Activations Density 0.017%

    No Known Activations