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. 5-GEMMASCOPE-RES-16K
    6. 4398
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions or diagnostic procedures, particularly in connection with respiratory syndromes and immunological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -1.21
    ValueStyle
    -0.71
    expandindo
    -0.68
     podjela
    -0.64
    adpleegd
    -0.62
     nahilalakip
    -0.61
    Diwedd
    -0.56
    @[+][
    -0.54
    ↵↵↵↵↵
    -0.54
    REFUND
    -0.52
    POSITIVE LOGITS
    </strong>
    1.81
    </b>
    1.64
    </u>
    1.58
    </em>
    1.41
    </h2>
    1.35
    </i>
    1.20
    </h4>
    1.12
    </code>
    1.08
    </h5>
    0.92
    </h3>
    0.90
    Activations Density 2.329%

    No Known Activations