© 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. 31-GEMMASCOPE-RES-131K
    11. 87297
    Prev
    Next
    INDEX
    Explanations

    references to ethical or consent-related terms in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     keuken
    -0.37
     türlü
    -0.35
     picioare
    -0.35
     esempi
    -0.34
     Küchen
    -0.33
    億円
    -0.32
     piese
    -0.32
     mijne
    -0.31
     zijne
    -0.31
     scare
    -0.31
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    ScopeManager
    0.78
     يتيمه
    0.74
    AddTagHelper
    0.66
    KommentareTeilen
    0.64
    帖最后由
    0.63
    脚注の使い方
    0.61
     noDo
    0.60
     kaarangay
    0.59
    SourceChecksum
    0.59
    Activations Density 0.000%

    No Known Activations