© 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
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 7314
    Prev
    Next
    INDEX
    Explanations

    actions related to disobedience and misconduct within a correctional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.62
    webElementXpaths
    -0.60
    zzleHttp
    -0.59
    rungsseite
    -0.57
    addCriterion
    -0.56
    routeProvider
    -0.55
     disambiguazione
    -0.54
     ffilmiau
    -0.54
    Legături
    -0.52
    ngdoc
    -0.52
    POSITIVE LOGITS
     instructions
    0.54
     instruction
    0.46
     instrucciones
    0.42
     instru
    0.42
     assigned
    0.41
     Instr
    0.40
    指示
    0.40
     instr
    0.39
    Instr
    0.38
    ordnungen
    0.36
    Activations Density 0.574%

    No Known Activations