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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9760
    Prev
    Next
    INDEX
    Explanations

    numerical values and mathematical concepts

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     المعيارى
    -0.84
     Wiktionnaire
    -0.74
    
    -0.71
     ujednoznacz
    -0.70
    CodedInputStream
    -0.69
    PreferredItem
    -0.69
     Shakspeare
    -0.69
    paraíso
    -0.67
    ceq
    -0.64
    -------------</
    -0.63
    POSITIVE LOGITS
    cshtml
    0.63
     ModelExpression
    0.53
    蒸し
    0.49
    تفصیلات
    0.46
     matter
    0.46
    ↵↵
    0.42
     zprá
    0.40
    暴
    0.39
    greenrobot
    0.39
     faite
    0.38
    Activations Density 0.026%

    No Known Activations