© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105410
    Prev
    Next
    INDEX
    Explanations

    instances of a character being incarcerated or discussing jail-related experiences

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

    jail, prison, or bed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BitmapFactory
    -0.38
     kuliner
    -0.32
    期刊论文
    -0.31
     noqa
    -0.30
     chi̍t
    -0.29
    GrantedAuthority
    -0.29
     Sahne
    -0.28
     AssemblyCulture
    -0.27
     durabilidad
    -0.27
     hígado
    -0.27
    POSITIVE LOGITS
    contentLoaded
    0.73
     يتيمه
    0.63
    ніципалі
    0.62
     محفوظة
    0.59
    ScopeManager
    0.55
    点此举报
    0.53
    MessageOf
    0.52
     queſta
    0.52
    WriteTagHelper
    0.52
    hospital
    0.51
    Activations Density 0.048%

    No Known Activations