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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4751
    Prev
    Next
    INDEX
    Explanations

    references to the concept of influence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roveň
    -0.64
    setVerticalGroup
    -0.62
    argout
    -0.62
    полнитель
    -0.61
     Ching
    -0.60
    ically
    -0.60
     majeurs
    -0.59
    utuhkan
    -0.59
    storms
    -0.58
    RuleContext
    -0.58
    POSITIVE LOGITS
    $',
    0.67
    e
    0.62
    ]};
    0.61
    ']?>
    0.60
    ANCE
    0.59
    ing
    0.59
    }}}{
    0.58
    __":
    0.58
    )}}{
    0.56
    ments
    0.56
    Activations Density 0.179%

    No Known Activations