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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 1764
    Prev
    Next
    INDEX
    Explanations

    references to specific file paths and images in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.77
    StructEnd
    -0.69
    ')))
    -0.67
     isInitialized
    -0.67
    Jeografia
    -0.67
    ')")
    -0.66
    writeFieldEnd
    -0.66
    ↩
    -0.64
    ")))
    -0.63
    ].)
    -0.61
    POSITIVE LOGITS
    tvguidetime
    0.69
    \_
    0.62
    出版年
    0.61
     Coliseum
    0.52
     Excerpt
    0.50
     Stell
    0.50
     Magnolia
    0.49
    VersionUID
    0.49
    onViewCreated
    0.48
     Reſ
    0.48
    Activations Density 0.076%

    No Known Activations