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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8590
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and judicial context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InjectAttribute
    -0.59
    AxisAlignment
    -0.59
    .";
    -0.57
     ?";
    -0.57
    '>
    
    -0.55
    '}>
    -0.54
    請繼續往下閱讀
    -0.54
    '},
    
    -0.54
    ?”,
    -0.54
     autorytatywna
    -0.53
    POSITIVE LOGITS
    ↵↵↵↵
    2.77
    ↵↵↵↵↵
    2.31
    ↵↵↵↵↵↵
    2.25
    ↵↵↵↵↵↵↵↵
    2.11
    ↵↵↵↵↵↵↵
    2.05
    ↵↵↵↵↵↵↵↵↵↵
    1.86
    ↵↵↵↵↵↵↵↵↵
    1.84
    ↵↵↵↵↵↵↵↵↵↵↵
    1.75
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.71
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.65
    Activations Density 0.686%

    No Known Activations