Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 92316
    Prev
    Next
    INDEX
    Explanations

    items and components related to vehicles and machinery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     CreateTagHelper
    -0.60
     cherchés
    -0.59
    AndEndTag
    -0.57
     ſind
    -0.57
    Rptr
    -0.54
     Theſe
    -0.53
    NSYLVANIA
    -0.52
    expertise
    -0.52
    ález
    -0.52
     ſeveral
    -0.52
    POSITIVE LOGITS
    SupportActionBar
    0.35
    ActionBar
    0.31
    top
    0.30
    pass
    0.29
    getItemId
    0.28
     Bienen
    0.28
    GOL
    0.27
     mergeFrom
    0.27
     placa
    0.27
    ride
    0.27
    Activations Density 0.033%

    No Known Activations