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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114893
    Prev
    Next
    INDEX
    Explanations

    actions related to biological sample preparation and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     anti
    -0.31
    PointerException
    -0.30
     distanciation
    -0.29
     ComVisible
    -0.29
    djangoproject
    -0.29
    CreateInfo
    -0.27
    ToScroll
    -0.26
     Numerade
    -0.26
     trust
    -0.26
    InputTagHelper
    -0.26
    POSITIVE LOGITS
    captured
    0.68
     utafitiHapana
    0.67
    collected
    0.65
    arangay
    0.60
    最快更新
    0.60
    AutoScaleMode
    0.58
    MessageOf
    0.58
    rungsseite
    0.58
    collecting
    0.57
    delwed
    0.57
    Activations Density 0.237%

    No Known Activations