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. 20-GEMMASCOPE-RES-16K
    6. 12926
    Prev
    Next
    INDEX
    Explanations

    expressions and variables in a coding or scripting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     "");
    -0.64
     $"
    -0.60
    }{*}{}
    -0.57
    BERTO
    -0.57
     "'");
    -0.56
     '');
    -0.56
     "");
    
    -0.55
     INTERESAR
    -0.55
    ')['
    -0.55
    ogado
    -0.54
    POSITIVE LOGITS
    (((
    0.61
    évaluateur
    0.61
    GOTREF
    0.60
    httphttps
    0.59
     Bumble
    0.59
    ((((
    0.58
    Географи
    0.57
    ьаж
    0.54
     Jordi
    0.53
    insertar
    0.52
    Activations Density 0.160%

    No Known Activations