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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1832
    Prev
    Next
    INDEX
    Explanations

    expressions of shared experiences and emotional connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    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
    new
    -0.48
     new
    -0.46
     Dob
    -0.44
     err
    -0.43
    seth
    -0.41
     directions
    -0.40
    équ
    -0.40
     C
    -0.40
    mend
    -0.40
     Sie
    -0.40
    POSITIVE LOGITS
    ThroughAttribute
    1.15
    InjectAttribute
    1.03
    Geplaatst
    1.00
     ModelExpression
    0.97
    ScopeManager
    0.97
    AddTagHelper
    0.96
     Мексичка
    0.95
     BoxFit
    0.94
    AnimationsModule
    0.94
    RenderAtEndOf
    0.93
    Activations Density 0.115%

    No Known Activations