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. 18-GEMMASCOPE-RES-16K
    6. 10138
    Prev
    Next
    INDEX
    Explanations

    parsing or formatting functions and command syntax in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     figliu
    -0.58
    EREF
    -0.56
     contextLoads
    -0.56
    Enllaces
    -0.56
     bäst
    -0.53
    SetTitle
    -0.52
    🔕
    -0.52
     déclar
    -0.51
    ecare
    -0.51
    destroyAll
    -0.51
    POSITIVE LOGITS
    '));
    
    0.71
    "))
    
    0.66
    ")));
    0.64
    "),
    
    0.64
    :");
    
    0.63
    "));
    
    0.63
    ')));
    0.63
    "))
    0.62
    ()]
    
    0.62
    ()])
    0.60
    Activations Density 0.104%

    No Known Activations