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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 12824
    Prev
    Next
    INDEX
    Explanations

    patterns or structures within mathematical or programming expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}</
    -0.75
    gran
    -0.69
     Fron
    -0.68
    Fron
    -0.67
     InputDecoration
    -0.66
     GetEnumerator
    -0.65
    ρά
    -0.65
     MessageBoxIcon
    -0.64
     Dign
    -0.63
    )");
    
    -0.63
    POSITIVE LOGITS
     *
    1.97
    *
    1.81
    !*
    1.67
    ?*
    1.65
    :*
    1.64
    ()*
    1.58
    .*
    1.58
    -*
    1.50
    >*
    1.47
     $*$
    1.46
    Activations Density 0.860%

    No Known Activations