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. 1014
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation related to monetary values or variables in mathematical contexts

    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
    ly
    -0.78
    es
    -0.60
    ться
    -0.55
    ,
    -0.53
    <blockquote>
    -0.53
    mento
    -0.51
    λιά
    -0.51
    но
    -0.49
    ling
    -0.48
    _
    -0.48
    POSITIVE LOGITS
    httphttps
    1.11
     مشين
    1.03
    "])
    
    0.99
    MigrationBuilder
    0.97
    RenderAtEndOf
    0.97
     }}$,
    0.96
     }}$
    0.95
     @"/
    0.94
    ]`
    0.93
    ]$}
    0.93
    Activations Density 0.498%

    No Known Activations