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. 10-GEMMASCOPE-RES-16K
    6. 12343
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to chart layouts and data visualization in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.38
    脚注の使い方
    -0.37
     الاطلاع
    -0.36
     atún
    -0.35
    })));
    -0.34
     desenho
    -0.31
     gawas
    -0.30
    }`;
    -0.29
     désert
    -0.29
    desenho
    -0.29
    POSITIVE LOGITS
    typeorm
    0.72
    InitVars
    0.64
    $_['
    0.63
     HttpNotFound
    0.63
     dAtA
    0.62
     समीक्षाओं
    0.61
     propOrder
    0.60
    ContextHolder
    0.57
    Rüyada
    0.57
    المكان
    0.56
    Activations Density 2.634%

    No Known Activations