© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13200
    Prev
    Next
    INDEX
    Explanations

    keywords related to inappropriate or improper behaviors and actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    something is not correct

    np_acts-logits-general · gemini-2.0-flash

    improper or abnormal states

    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
    Negative Logits
    хьтан
    -0.45
    makeText
    -0.43
    httphttps
    -0.43
    Tracce
    -0.41
    CEP
    -0.41
     createSprite
    -0.39
     voordeel
    -0.39
    blockList
    -0.38
    KURZBESCHREIBUNG
    -0.37
    出版年
    -0.37
    POSITIVE LOGITS
     unangemessene
    0.60
    nappropriate
    0.60
    Inappropriate
    0.56
     Deviant
    0.55
     inappropriate
    0.54
     unbalanced
    0.53
     aberrant
    0.52
     unsound
    0.51
     ErrInvalid
    0.51
     inconsistent
    0.51
    Activations Density 0.664%

    No Known Activations