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. 15-GEMMASCOPE-RES-16K
    6. 2824
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics in the text

    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
    endpush
    -0.65
    expandindo
    -0.61
     سكانية
    -0.57
     مرئيه
    -0.56
    
    -0.55
    GEBURTS
    -0.54
     étrangers
    -0.53
    Tembelea
    -0.49
    AutoScaleMode
    -0.49
    Personendaten
    -0.48
    POSITIVE LOGITS
    ArrowToggle
    0.63
    ########.
    0.56
    astéroïdes
    0.55
    ocy
    0.53
    Бахар
    0.52
    $_['
    0.51
    cshtml
    0.51
    Hentet
    0.51
    Toro
    0.49
    indeer
    0.49
    Activations Density 0.427%

    No Known Activations