© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12103
    Prev
    Next
    INDEX
    Explanations

    dialogues involving conflict and emotional interactions between characters

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

    said or done by a person/character

    np_acts-logits-general · gemini-2.0-flash

    actions immediately following names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Kariera
    -0.54
    bottomrule
    -0.49
    گاب
    -0.45
     servi
    -0.44
    rzost
    -0.43
     voort
    -0.43
    覿
    -0.43
     Lane
    -0.42
     Nor
    -0.41
     Truman
    -0.41
    POSITIVE LOGITS
     clicked
    0.48
     groaned
    0.44
     wept
    0.41
    sekten
    0.40
     counted
    0.40
     walked
    0.40
     darse
    0.39
     danced
    0.39
     menatap
    0.38
     bounced
    0.38
    Activations Density 0.187%

    No Known Activations