© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9816
    Prev
    Next
    INDEX
    Explanations

    conditional statements or uncertainties affecting outcomes

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

    Follows conditional words ("if," "case," "whatever")

    np_acts-logits-general · gemini-2.0-flash

    conditional outcomes

    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
     havia
    -0.35
     content
    -0.34
     Einblick
    -0.33
     Pin
    -0.32
    makeText
    -0.31
     widok
    -0.31
     fazia
    -0.30
    assemblée
    -0.30
     proprement
    -0.30
     kwenye
    -0.29
    POSITIVE LOGITS
    TagMode
    0.69
    AndEndTag
    0.63
    Hentet
    0.63
    FormTagHelper
    0.59
    abestanden
    0.57
     الرخصة
    0.55
     ModelExpression
    0.54
    gameserver
    0.54
    httphttps
    0.54
    gdx
    0.54
    Activations Density 0.334%

    No Known Activations