© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1919
    Prev
    Next
    INDEX
    Explanations

    elements like code snippets or commands related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, file paths, and programming-related text

    np_acts-logits-general · gemini-2.0-flash

    formatting and document structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.74
    ArrowToggle
    -0.65
    Specifiche
    -0.65
    LEGGI
    -0.64
     Vikipedi
    -0.63
    請繼續往下閱讀
    -0.63
    ांकि
    -0.62
    dollis
    -0.62
    ſelves
    -0.61
    Gambas
    -0.60
    POSITIVE LOGITS
    <eos>
    1.13
    </b>
    0.65
    <h1>
    0.64
    <h2>
    0.64
    ');
    0.64
    ");
    0.62
    });
    0.61
    ↵↵
    0.60
    ↵↵↵↵
    0.59
    ↵↵↵↵↵
    0.59
    Activations Density 0.974%

    No Known Activations