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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 24041
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical concepts and structures

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

    lack of, absence of

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Personensuche
    -1.07
     gynhyrchwyd
    -0.68
     esternos
    -0.67
    ReusableCell
    -0.66
    IBarButtonItem
    -0.66
    writeFieldEnd
    -0.66
    ContentAsync
    -0.64
    ItemBackground
    -0.64
    JspWriter
    -0.64
     informée
    -0.63
    POSITIVE LOGITS
    .
    0.35
    ↵
    0.32
    log
    0.28
    pot
    0.28
     Inter
    0.26
    roy
    0.26
     Choi
    0.26
     Lib
    0.26
     ins
    0.25
    Log
    0.25
    Activations Density 0.111%

    No Known Activations