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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6813
    Prev
    Next
    INDEX
    Explanations

    culinary descriptors related to food preparation and quality

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

    that intensify adjectives

    np_acts-logits-general · gemini-2.0-flash

    adverbs of degree or manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.85
     snippetHide
    -0.69
    AnimationsModule
    -0.60
    rungsseite
    -0.55
    RenderAtEndOf
    -0.54
    transQ
    -0.54
     consultato
    -0.53
    Hochspringen
    -0.53
     démarche
    -0.51
    -------------</
    -0.51
    POSITIVE LOGITS
     thoroughly
    0.60
     Thorough
    0.58
     juicy
    0.55
    たっぷ
    0.55
     hefty
    0.55
    plenty
    0.54
    oughly
    0.54
    たっぷり
    0.54
     ample
    0.53
     plenty
    0.52
    Activations Density 0.327%

    No Known Activations