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

    Neuronpedia

    APICircuit 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. 21-GEMMASCOPE-RES-16K
    6. 6464
    Prev
    Next
    INDEX
    Explanations

    code structure and control flow elements, particularly loops and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.99
    $.\\
    -0.95
    例文帳に追加
    -0.89
    ).\\
    -0.84
    }$.\\
    -0.83
    }}$\\
    -0.81
    .\\
    -0.79
    ↵↵↵
    -0.77
    $\\
    -0.69
    」。
    -0.67
    POSITIVE LOGITS
    ();)
    1.13
    ;)
    0.99
    </u>
    0.89
    ;++
    0.84
    </strong>
    0.83
    ;
    0.83
    </em>
    0.70
    </b>
    0.68
    ;;)
    0.68
     ;
    0.67
    Activations Density 0.057%

    No Known Activations