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. 13966
    Prev
    Next
    INDEX
    Explanations

    statements that assert the existence or importance of a subject

    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
     ModelExpression
    -1.13
    InjectAttribute
    -0.99
    StoryboardSegue
    -0.95
    
    -0.92
     autorytatywna
    -0.90
    OGND
    -0.87
     nakalista
    -0.84
    :✨
    -0.84
    principalColumn
    -0.82
     BIBSYS
    -0.82
    POSITIVE LOGITS
     why
    0.85
     how
    0.85
     where
    0.69
     the
    0.69
     done
    0.66
     allemaal
    0.65
     true
    0.64
     because
    0.61
     especially
    0.58
     happening
    0.58
    Activations Density 0.177%

    No Known Activations