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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 15695
    Prev
    Next
    INDEX
    Explanations

    the keyword "inline" in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 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
    mybatisplus
    -0.84
     McClure
    -0.81
     plates
    -0.80
     StatefulWidget
    -0.80
     Gell
    -0.79
    BindView
    -0.77
    شق
    -0.76
    rakt
    -0.76
    mayer
    -0.75
     Fiz
    -0.74
    POSITIVE LOGITS
    inline
    1.15
    Inline
    1.02
     Inline
    0.94
     inline
    0.92
    ]-->
    0.86
    INLINE
    0.86
    }();
    0.75
     Waray
    0.73
     --}}
    0.71
    monials
    0.71
    Activations Density 0.194%

    No Known Activations