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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 114929
    Prev
    Next
    INDEX
    Explanations

    phrases indicating needs or demands for improvements or solutions

    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
    CppMethod
    -0.34
    FunctionFlags
    -0.33
    monary
    -0.32
     disambiguazione
    -0.32
     reac
    -0.32
    Aprove
    -0.31
     iNdEx
    -0.31
     Charities
    -0.30
    ativement
    -0.30
    }');
    -0.30
    POSITIVE LOGITS
    webElementGuid
    0.49
     solution
    0.49
    bootstrapcdn
    0.48
     nahilalakip
    0.48
    providedIn
    0.48
     DbSet
    0.47
     solutions
    0.46
    solution
    0.46
     oplossing
    0.45
    Бахар
    0.44
    Activations Density 0.113%

    No Known Activations