© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10796
    Prev
    Next
    INDEX
    Explanations

    terms related to the legal and sentencing process

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

    prison or inmates

    np_acts-logits-general · gemini-2.0-flash

    prison inmates and sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saraba
    -0.63
    apimachinery
    -0.59
    VERTISING
    -0.55
     resourceCulture
    -0.52
     surla
    -0.47
    plevel
    -0.46
     tant
    -0.43
    SourceChecksum
    -0.43
     fainted
    -0.43
    ruik
    -0.42
    POSITIVE LOGITS
     prison
    1.80
     Prison
    1.65
     prisoner
    1.59
    Prison
    1.58
     inmate
    1.58
    prison
    1.56
     prisons
    1.56
     prisoners
    1.55
     inmates
    1.51
     PRISON
    1.47
    Activations Density 1.042%

    No Known Activations