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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3827
    Prev
    Next
    INDEX
    Explanations

    markup or coding elements in the text

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

    Code snippets or code-related syntax

    np_acts-logits-general · gemini-2.0-flash

    code syntax and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Conoce
    -0.43
    Is
    -0.42
    nya
    -0.40
     hear
    -0.40
    Также
    -0.40
     also
    -0.40
     Is
    -0.39
    ly
    -0.39
    lyn
    -0.39
    DBC
    -0.39
    POSITIVE LOGITS
    </blockquote>
    1.73
    ();*/
    0.75
    )";
    
    0.74
    +#+
    0.73
    };*/
    0.71
    !";
    0.71
    \]
    0.71
     ligiloj
    0.69
    arangay
    0.69
    /***/
    0.69
    Activations Density 0.416%

    No Known Activations