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. 36751
    Prev
    Next
    INDEX
    Explanations

    specific topics or categories related to various forms of data and biological entities

    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
    Datuak
    -0.73
     مشين
    -0.73
    RenderAtEndOf
    -0.71
    ########.
    -0.71
    ]=>
    -0.69
    ftagPool
    -0.66
     дописавши
    -0.65
    @[+][
    -0.63
     surla
    -0.63
     utafitiHapana
    -0.61
    POSITIVE LOGITS
    клопе
    0.60
    LookAnd
    0.57
    RoutingModule
    0.57
    下载附件
    0.52
     ſeveral
    0.51
    emptory
    0.50
    MoveNext
    0.50
    leſs
    0.49
    HasColumnType
    0.48
    Ữ
    0.48
    Activations Density 0.878%

    No Known Activations