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. 13-GEMMASCOPE-RES-16K
    6. 7369
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation used in abstract concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DUCT
    -0.44
     shutil
    -0.41
    бля
    -0.39
    </b>
    -0.39
     Leben
    -0.38
    qui
    -0.37
     aver
    -0.37
     ч
    -0.37
     too
    -0.37
    udur
    -0.37
    POSITIVE LOGITS
    providedIn
    1.02
    OGND
    0.96
     referenties
    0.95
     BorderRadius
    0.94
     متعلقه
    0.94
    +#+
    0.92
    ImageContext
    0.92
    MigrationBuilder
    0.91
    fillType
    0.89
    حوالہ
    0.88
    Activations Density 1.349%

    No Known Activations