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. 8686
    Prev
    Next
    INDEX
    Explanations

    terms related to legal cases and academic references

    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
     ་་
    -1.34
    BibitemShut
    -1.33
    >\<^
    -1.32
     itſelf
    -1.28
    )");
    
    -1.22
    leſs
    -1.15
     iſt
    -1.13
    )";
    
    -1.10
     ―――――
    -1.10
     myſelf
    -1.08
    POSITIVE LOGITS
    r
    0.89
    op
    0.86
    b
    0.83
    ra
    0.80
    z
    0.80
    ol
    0.78
    Z
    0.75
    P
    0.74
    li
    0.73
    v
    0.73
    Activations Density 1.874%

    No Known Activations