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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12875
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to parts, components, or ingredients of things, especially in natural or biological contexts.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    terms related to coal, charcoal, and biomass materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     indé
    -0.37
     তারিখ
    -0.35
    };*/
    -0.34
     FetchType
    -0.33
     "];
    -0.32
     успе
    -0.31
     Enkel
    -0.31
    staben
    -0.31
     custa
    -0.31
     }}</
    -0.30
    POSITIVE LOGITS
     waste
    0.69
    waste
    0.63
     wastes
    0.60
     Waste
    0.59
    Waste
    0.58
     discarded
    0.57
     déchets
    0.56
     desperdic
    0.52
     disposal
    0.51
     WASTE
    0.51
    Activations Density 0.253%

    No Known Activations