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. 15-GEMMASCOPE-RES-16K
    6. 2404
    Prev
    Next
    INDEX
    Explanations

    technical terms and instructions related to software and programming scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     }}$}
    -0.73
    '));
    
    -0.66
     MessageBoxIcon
    -0.64
    //
    -0.63
    Демографія
    -0.63
    reszcie
    -0.61
     Chapitre
    -0.60
    jsonwebtoken
    -0.60
    Xna
    -0.60
    )");
    
    -0.60
    POSITIVE LOGITS
     following
    0.56
    AndEndTag
    0.56
    以下
    0.52
    ow
    0.52
    paž
    0.51
    ANY
    0.51
     yourself
    0.50
     paire
    0.50
     Following
    0.50
     optionally
    0.49
    Activations Density 0.648%

    No Known Activations