© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 27782
    Prev
    Next
    INDEX
    Explanations

    terms related to addiction and dependence, particularly in the context of substances or behaviors that are enjoyable or have a strong appeal

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

    stickiness, addictive, hysteresis, contagious disease, seeding, adhesion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    大利
    -0.44
     Sod
    -0.39
    喫
    -0.39
     demografica
    -0.38
     bakgrund
    -0.37
    relevant
    -0.36
    🇴
    -0.36
     bienes
    -0.35
    OfBirth
    -0.35
    ponses
    -0.35
    POSITIVE LOGITS
    sticky
    0.68
    Sticky
    0.66
     sticky
    0.66
     addictive
    0.60
     Sticky
    0.58
     catchy
    0.57
     AssemblyCulture
    0.57
    AndEndTag
    0.57
     hook
    0.53
    Hook
    0.51
    Activations Density 0.073%

    No Known Activations