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. 105170
    Prev
    Next
    INDEX
    Explanations

    interactions and dynamics within personal relationships

    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
     kasarigan
    -0.46
    libft
    -0.42
     PUR
    -0.39
    IsContent
    -0.39
     Seventh
    -0.38
    umlu
    -0.38
     dårlig
    -0.38
     حر
    -0.37
    tvguidetime
    -0.36
    PUR
    -0.36
    POSITIVE LOGITS
    GTCX
    0.61
    MLLoader
    0.56
    SourceChecksum
    0.51
    AnchorTagHelper
    0.50
    homonymie
    0.50
    ">//
    0.49
     lizenzfreies
    0.48
     дописавши
    0.46
    이션
    0.45
    ípios
    0.45
    Activations Density 0.064%

    No Known Activations