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. 7750
    Prev
    Next
    INDEX
    Explanations

    elements related to guidance and recommendations in a procedural context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after common prefixes

    np_acts-logits-general · gemini-2.0-flash

    criminal history

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     totiž
    -0.62
    <eos>
    -0.59
     whichever
    -0.57
     either
    -0.55
     -,
    -0.55
     appunto
    -0.55
     acestei
    -0.54
     zowel
    -0.53
     effectually
    -0.51
     zarówno
    -0.50
    POSITIVE LOGITS
    </h2>
    1.60
    </h4>
    1.45
    </strong>
    1.38
    </h3>
    1.38
    }$}
    1.30
    )$}
    1.30
    </b>
    1.28
    </h5>
    1.24
    ]$}
    1.23
    ")]
    
    1.22
    Activations Density 0.476%

    No Known Activations