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. 20-GEMMASCOPE-RES-16K
    6. 9185
    Prev
    Next
    INDEX
    Explanations

    technical terms related to audio synthesis and electronic music equipment

    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
    MIDDLEWARE
    -0.73
    MethodManager
    -0.70
    HttpFoundation
    -0.69
    gonic
    -0.69
     <=",
    -0.68
     magasiner
    -0.66
    esgue
    -0.63
    новниш
    -0.63
    zzleHttp
    -0.61
    SerializedSize
    -0.60
    POSITIVE LOGITS
     nahilalakip
    0.67
     autorytatywna
    0.65
    </i>
    0.61
    </h3>
    0.54
    </em>
    0.51
    </blockquote>
    0.49
    );*/
    0.47
    </h6>
    0.45
    NotFoundError
    0.44
    。』
    0.43
    Activations Density 8.033%

    No Known Activations