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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36685
    Prev
    Next
    INDEX
    Explanations

    references to the "self" keyword, indicating object-oriented programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.94
    تقاوى
    -0.91
    StructEnd
    -0.69
    colage
    -0.68
    adpleegd
    -0.68
    RegressionTest
    -0.66
    SuppressMessage
    -0.66
    ябре
    -0.65
     Rasul
    -0.63
     يتيمه
    -0.62
    POSITIVE LOGITS
    Personendaten
    0.60
    providedIn
    0.56
     unknownFields
    0.54
    Eksteraj
    0.51
     OnInit
    0.50
    tagHelperRunner
    0.50
    Ссылки
    0.48
    formik
    0.47
    半身
    0.47
    migrationBuilder
    0.47
    Activations Density 0.001%

    No Known Activations