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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 845
    Prev
    Next
    INDEX
    Explanations

    code structure elements and syntax within programming context

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

    Code-related keywords and syntax

    np_acts-logits-general · gemini-2.0-flash

    proceed in steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    참고
    -0.69
    RatingBar
    -0.66
     Roskov
    -0.63
    verwijspagina
    -0.63
    তথ্যসূত্র
    -0.63
    Vidite
    -0.61
    Посилання
    -0.61
    ühnen
    -0.60
     hyg
    -0.60
     ligiloj
    -0.59
    POSITIVE LOGITS
     const
    0.57
    };
    0.49
    );
    0.48
     ModelExpression
    0.46
    ];
    0.46
    const
    0.45
     useState
    0.44
    naio
    0.42
    ↵
    0.41
    cioc
    0.41
    Activations Density 0.196%

    No Known Activations