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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-GEMMASCOPE-RES-16K
    6. 12952
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and medical processes or studies

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

    "during"

    np_acts-logits-general · gemini-2.0-flash

    during

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.68
    servable
    -0.56
    +#+#
    -0.56
    neum
    -0.54
    ળ
    -0.52
    chymal
    -0.50
    UserScript
    -0.49
    providedIn
    -0.48
    toplas
    -0.47
    igslist
    -0.47
    POSITIVE LOGITS
     during
    3.42
    during
    3.01
     During
    2.86
    During
    2.77
     DURING
    2.76
     durante
    2.67
    durante
    2.35
     tijdens
    2.33
    Durante
    2.24
     Durante
    2.18
    Activations Density 1.121%

    No Known Activations