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. 75461
    Prev
    Next
    INDEX
    Explanations

    conjunctions and logical operators in text

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

    terms connected by "or" or "and"

    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
    internalType
    -0.35
     needs
    -0.32
     with
    -0.31
     that
    -0.28
     թվական
    -0.26
     has
    -0.26
     aka
    -0.26
    venez
    -0.25
     있어
    -0.25
     onely
    -0.25
    POSITIVE LOGITS
    RenderAtEndOf
    0.70
    +:+
    0.64
    tanleria
    0.62
    StoreMessageInfo
    0.60
    .*")]
    0.58
     Meksiku
    0.58
    oredCriteria
    0.57
    تقاوى
    0.57
     kasarigan
    0.57
    +#+#
    0.55
    Activations Density 0.046%

    No Known Activations