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. 1845
    Prev
    Next
    INDEX
    Explanations

    expressions of love and care for others

    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
     يتيمه
    -0.59
    Jeografia
    -0.56
     intptr
    -0.56
     Utile
    -0.54
    OfMonth
    -0.52
    tan
    -0.51
     समीक्षक
    -0.50
    tvguidetime
    -0.50
    ῖς
    -0.50
     Klick
    -0.50
    POSITIVE LOGITS
     kasarigan
    0.68
     TextAlign
    0.59
     Roskov
    0.56
    :][
    0.56
    ={({
    0.54
    dflare
    0.51
    jsonwebtoken
    0.51
    دانشنامهٔ
    0.51
    IMDG
    0.50
    mapStateToProps
    0.50
    Activations Density 0.156%

    No Known Activations