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. 1848
    Prev
    Next
    INDEX
    Explanations

    references to assistance or support in various forms

    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
    stra
    -0.48
    しかったです
    -0.47
    
    -0.45
     engaged
    -0.45
    {\
    -0.45
    vician
    -0.43
    уза
    -0.43
     cartões
    -0.43
    cri
    -0.43
    ','
    -0.42
    POSITIVE LOGITS
     matters
    0.91
    matters
    0.81
     disambiguazione
    0.78
     Matters
    0.75
    ToAction
    0.75
    躇
    0.73
     việc
    0.73
    المناصب
    0.72
    เรื่อง
    0.71
    requestCode
    0.69
    Activations Density 0.320%

    No Known Activations