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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 6417
    Prev
    Next
    INDEX
    Explanations

    mentions of healthcare conditions and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -1.06
     Shakspeare
    -0.92
     betweenstory
    -0.92
     Roskov
    -0.92
    mybatisplus
    -0.91
     సౌకర్య
    -0.89
     doubtnut
    -0.86
     itſelf
    -0.85
    хьтан
    -0.84
     crdi
    -0.83
    POSITIVE LOGITS
    .
    0.72
    •
    0.71
    <eos>
    0.70
     The
    0.70
     
    0.67
    <td>
    0.66
    *
    0.65
    ?
    0.65
     And
    0.65
    ●
    0.62
    Activations Density 0.169%

    No Known Activations