© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1314
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory compliance and guidelines

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

    indebtedness exclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     velcro
    -0.45
     downright
    -0.45
     booze
    -0.44
    withOpacity
    -0.44
    mybatisplus
    -0.43
     Behavioural
    -0.42
    MethodManager
    -0.42
     sneaky
    -0.42
     salesman
    -0.41
     ottima
    -0.40
    POSITIVE LOGITS
    ništvo
    0.45
     whoſe
    0.43
     whofe
    0.41
     fubject
    0.41
     becauſe
    0.40
     Infórmanos
    0.40
    ftagPool
    0.40
     didst
    0.38
    gameserver
    0.38
    hashtags
    0.38
    Activations Density 0.016%

    No Known Activations