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. 45772
    Prev
    Next
    INDEX
    Explanations

    references to software functionality and user guidance

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

    contractions and 'out 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
     inspired
    -0.35
     supporting
    -0.35
     and
    -0.34
    ,
    -0.32
    WebElementEntity
    -0.31
     measured
    -0.30
    anstalt
    -0.30
    ftagPool
    -0.30
     geblieben
    -0.29
    filled
    -0.29
    POSITIVE LOGITS
    httphttps
    0.77
    principalColumn
    0.66
    ंदीखरीदारी
    0.65
     utafitiHapana
    0.65
     Wiktionnaire
    0.63
    匿名使用者
    0.62
    findpost
    0.60
    帖最后由
    0.60
     Meksiku
    0.59
    LookAnd
    0.58
    Activations Density 0.831%

    No Known Activations