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. 13548
    Prev
    Next
    INDEX
    Explanations

    citations and references in scientific contexts

    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
    AsUp
    -0.72
    GEBURTSDATUM
    -0.67
    PerformLayout
    -0.61
    fjspx
    -0.60
    Hozzáférés
    -0.58
    TypedDataSet
    -0.57
     kasarigan
    -0.54
    lexikon
    -0.54
    دانشنامهٔ
    -0.54
    ########.
    -0.53
    POSITIVE LOGITS
     Efq
    0.62
    esModule
    0.58
    noons
    0.57
     Affiliations
    0.57
     lenker
    0.55
     grantor
    0.54
     تانيه
    0.54
    WEBPACK
    0.54
     appellant
    0.54
     ibid
    0.51
    Activations Density 0.007%

    No Known Activations