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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14259
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structures and type definitions

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

    Mathematical or code-related square root functions

    np_acts-logits-general · gemini-2.0-flash

    keywords followed by parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    -1.11
    ];
    -1.04
     };
    -1.02
    ();
    -0.98
     "";
    -0.90
    );
    -0.87
     '';
    -0.86
     {};
    -0.86
     ];
    -0.85
    };
    -0.85
    POSITIVE LOGITS
    Portail
    0.71
    makeText
    0.59
     Vikipedi
    0.56
    genstein
    0.56
     ThemeData
    0.56
    contentLoaded
    0.56
    elemField
    0.55
    richTextPanel
    0.55
     Вікіпе
    0.54
    YourGuide
    0.54
    Activations Density 0.424%

    No Known Activations