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. 1791
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and legal terms

    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
    WindowConstants
    -0.73
    assium
    -0.71
    UCKY
    -0.60
    твра
    -0.59
    apeno
    -0.59
    okovic
    -0.57
    esgue
    -0.57
    hatsu
    -0.56
    αρα
    -0.56
    omitempty
    -0.56
    POSITIVE LOGITS
     of
    1.88
    Portail
    1.07
     của
    0.96
    ของ
    0.94
    of
    0.93
     Of
    0.81
     ofthe
    0.73
     OF
    0.71
     των
    0.71
     ऑफ
    0.71
    Activations Density 0.517%

    No Known Activations