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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 642
    Prev
    Next
    INDEX
    Explanations

    special character sequences and specific formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '},
    
    -0.87
    setVerticalGroup
    -0.85
    WebElementEntity
    -0.79
    %]
    -0.73
    %"),
    -0.73
    "):
    
    -0.72
    Autoritní
    -0.70
    ⎠
    -0.68
    '})
    -0.67
    %\]
    -0.67
    POSITIVE LOGITS
    󠁢
    0.54
     <<<<<<<<<<<<<<
    0.51
    ↵↵↵
    0.49
    oredCriteria
    0.48
     Wonderful
    0.48
     passim
    0.47
     pudesse
    0.47
    ↵↵
    0.46
    اعمال
    0.45
     spion
    0.45
    Activations Density 1.006%

    No Known Activations