Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12-GEMMASCOPE-RES-16K
    6. 5585
    Prev
    Next
    INDEX
    Explanations

    expressions of concern or fear regarding health risks or hazards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (")");
    -0.57
    antaine
    -0.52
     vitu
    -0.51
    atisk
    -0.50
    afficheront
    -0.49
     https
    -0.47
     '\\;'
    -0.47
    canestro
    -0.46
    ↵↵↵↵
    -0.46
     access
    -0.45
    POSITIVE LOGITS
     насељу
    0.84
    Abitanti
    0.77
     greateſt
    0.72
    VersionUID
    0.72
     culturelles
    0.69
     Профиль
    0.65
    NOPQRST
    0.65
     rilass
    0.62
     spéciaux
    0.62
     ſche
    0.62
    Activations Density 0.165%

    No Known Activations