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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14403
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax elements

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

    Prepositions, articles, and conjunctions

    np_acts-logits-general · gemini-2.0-flash

    novelty, crystal, lesion, taking, simply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    rizona
    -0.38
     labs
    -0.34
     inv
    -0.34
    OrNil
    -0.34
    WebServlet
    -0.34
     pey
    -0.33
    cB
    -0.33
     healing
    -0.33
    RTEE
    -0.33
     dew
    -0.32
    POSITIVE LOGITS
    참고
    0.59
    قایناقلار
    0.57
     semplicemente
    0.57
     autorytatywna
    0.57
     merely
    0.54
     simplement
    0.54
     simply
    0.54
     prostu
    0.53
     justru
    0.53
    simply
    0.52
    Activations Density 1.155%

    No Known Activations