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. 4892
    Prev
    Next
    INDEX
    Explanations

    occurrences of unusual formatting or punctuation in the text

    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
    énario
    -0.35
    weren
    -0.34
    podium
    -0.32
    StoryboardSegue
    -0.32
     Escolar
    -0.32
     couteau
    -0.31
    ‸
    -0.31
    mybatisplus
    -0.31
     Vulnerability
    -0.31
    ButterKnife
    -0.30
    POSITIVE LOGITS
     كومونز
    0.56
     AssemblyCulture
    0.54
     }}"></
    0.53
     lenker
    0.52
    UCS
    0.51
    IndentedString
    0.50
     الحره
    0.50
    msgTypes
    0.49
     ResponseEntity
    0.49
    ']>;
    0.48
    Activations Density 0.005%

    No Known Activations