© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102121
    Prev
    Next
    INDEX
    Explanations

    mentions of funding or support programs

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

    Language describing financial support programs, subsidies, or assistance offerings, including program names, eligibility requirements, benefit amounts, and application information.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ᅠ
    -0.28
    Espèce
    -0.27
    mär
    -0.27
    UC
    -0.27
    äjä
    -0.26
     "__
    -0.26
     unset
    -0.26
     gere
    -0.26
    äj
    -0.26
     mär
    -0.25
    POSITIVE LOGITS
     snippetHide
    0.62
    AndEndTag
    0.59
    parsedMessage
    0.58
     ModelRenderer
    0.57
     subsidized
    0.56
    Assistance
    0.55
    Programs
    0.54
     indígen
    0.54
    ementara
    0.54
    subsid
    0.54
    Activations Density 0.053%

    No Known Activations