Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 12945
    Prev
    Next
    INDEX
    Explanations

    specific references to medical and scientific terminology, particularly related to health conditions and research concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.80
    <eos>
    -0.35
    MathML
    -0.32
    </i>
    -0.30
    </tr>
    -0.29
    ’
    -0.28
    </b>
    -0.28
    ρυ
    -0.28
    нен
    -0.27
    </em>
    -0.27
    POSITIVE LOGITS
     Efq
    0.58
     Monfieur
    0.55
     myſelf
    0.55
     Majefty
    0.54
     ſeveral
    0.51
     purpoſe
    0.51
     Jefus
    0.51
     Theſe
    0.50
     themſelves
    0.49
     itſelf
    0.49
    Activations Density 53.872%

    No Known Activations