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. 58401
    Prev
    Next
    INDEX
    Explanations

    references to online content and live web events related to corporate announcements

    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
    MessageTagHelper
    -0.60
    ByExample
    -0.60
    WriteBarrier
    -0.57
    )}</
    -0.57
    CppMethod
    -0.56
    lossians
    -0.55
     Theſe
    -0.55
    NUMX
    -0.55
    ApiModel
    -0.53
    NameInMap
    -0.53
    POSITIVE LOGITS
    MENAFN
    0.65
    发表于
    0.62
    quiry
    0.54
    ########.
    0.54
     الاطلاع
    0.52
    ecap
    0.50
    sample
    0.50
    findpost
    0.48
    usepackage
    0.47
    AMPLE
    0.47
    Activations Density 0.004%

    No Known Activations