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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 6004
    Prev
    Next
    INDEX
    Explanations

    instances of emotional or physical intimacy between characters

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

    following "he" or ","

    np_acts-logits-general · gemini-2.0-flash

    actions and narrative events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nødvendig
    -0.39
     informée
    -0.35
    getOutputStream
    -0.33
    ForValue
    -0.30
     astr
    -0.30
     postIndex
    -0.30
    ArgumentParser
    -0.29
     impar
    -0.29
     geographic
    -0.29
    geography
    -0.29
    POSITIVE LOGITS
     CanadaChoose
    0.68
     motion
    0.56
     nodding
    0.52
     utafitiHapana
    0.51
     sitting
    0.51
     rolled
    0.50
     rolling
    0.50
    GEBURTSDATUM
    0.50
     Motion
    0.49
     waving
    0.49
    Activations Density 0.221%

    No Known Activations