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. 45642
    Prev
    Next
    INDEX
    Explanations

    action verbs that imply significant influence, change, or creation

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

    verbs ending in ing

    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
    <bos>
    -0.59
    Jeografia
    -0.57
    -------
    -0.49
    ']],
    -0.47
    mpo
    -0.46
    !="")
    -0.45
     %>
    -0.44
     
    -0.44
    Portale
    -0.44
     Guth
    -0.43
    POSITIVE LOGITS
    ing
    1.57
    ING
    1.09
    ة
    0.70
    ی
    0.69
    ckså
    0.68
    izing
    0.64
     يتيمه
    0.64
    BibitemShut
    0.64
    iſh
    0.62
    ſelf
    0.61
    Activations Density 0.163%

    No Known Activations