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. 0-GEMMASCOPE-RES-16K
    6. 130
    Prev
    Next
    INDEX
    Explanations

    words or phrases associated with biological and environmental interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -1.56
    SourceChecksum
    -1.48
     autorytatywna
    -1.46
    fjspx
    -1.45
     AssemblyCulture
    -1.44
     kaarangay
    -1.42
    تقاوى
    -1.42
    AndEndTag
    -1.42
     ویکی‌پدی
    -1.39
    LookAnd
    -1.39
    POSITIVE LOGITS
    .
    1.60
    ↵
    1.24
    </em>
    1.09
    </i>
    0.88
    <strong>
    0.85
    </blockquote>
    0.82
    [toxicity=0]
    0.78
    </h5>
    0.77
        
    0.73
    ,
    0.73
    Activations Density 10.631%

    No Known Activations