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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 12267
    Prev
    Next
    INDEX
    Explanations

    references to musical equipment and synthesizers, especially those involving the Yamaha Motif series and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    łów
    -0.38
    mark
    -0.36
    iman
    -0.36
    йс
    -0.36
    сме
    -0.36
     Rela
    -0.35
    uss
    -0.35
    xid
    -0.35
    tamol
    -0.35
     nada
    -0.34
    POSITIVE LOGITS
     виправивши
    0.95
    RenderAtEndOf
    0.81
     المعيارى
    0.80
     resourceCulture
    0.79
     referenties
    0.78
    complexContent
    0.77
     estekak
    0.76
     formato
    0.76
     formats
    0.75
     format
    0.74
    Activations Density 0.908%

    No Known Activations