© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4443
    Prev
    Next
    INDEX
    Explanations

    prepositions signifying locations or states of action in context

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

    "In" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    in effect or motion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVEREF
    -0.68
    HomeAsUpEnabled
    -0.59
    __(/*!
    -0.58
    setVerticalGroup
    -0.57
     dignité
    -0.53
    endmodule
    -0.53
     souha
    -0.52
    istoitu
    -0.51
     verschill
    -0.50
     bonté
    -0.50
    POSITIVE LOGITS
     play
    1.41
     use
    1.16
     existence
    1.09
     question
    1.07
     effect
    1.04
     force
    1.03
     operation
    1.02
     circulation
    1.01
    play
    0.98
     focus
    0.95
    Activations Density 0.376%

    No Known Activations