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. 8-GEMMASCOPE-RES-16K
    6. 5685
    Prev
    Next
    INDEX
    Explanations

    code snippets with specific variable assignments and string declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.75
     re
    -0.58
    ]');
    -0.53
    XmlAccessType
    -0.53
    Rüyada
    -0.52
    )]$
    -0.51
    `;
    
    -0.50
    ]");
    -0.49
    帖最后由
    -0.48
    argout
    -0.48
    POSITIVE LOGITS
    WireFormatLite
    0.67
     Jefus
    0.65
     cleanest
    0.64
     Chriftian
    0.63
    DockStyle
    0.62
     Chriſt
    0.61
     AssemblyCulture
    0.59
     Uff
    0.59
     utensils
    0.59
     Theſe
    0.59
    Activations Density 0.705%

    No Known Activations