© 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. 23-GEMMASCOPE-RES-16K
    11. 15194
    Prev
    Next
    INDEX
    Explanations

    phrases indicating decision-making considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    basicConfig
    -0.62
    oredCriteria
    -0.57
     الدولى
    -0.57
    Xna
    -0.56
    HasAnnotation
    -0.56
    RefNanny
    -0.55
    ędzynarod
    -0.53
     Roskov
    -0.53
    ckner
    -0.50
     jScrollPane
    -0.50
    POSITIVE LOGITS
     decision
    3.22
    decision
    2.90
     Decision
    2.73
    Decision
    2.71
     decisions
    2.65
     DECISION
    2.53
     Decisions
    2.48
    Decisions
    2.43
     décision
    2.39
    decisions
    2.35
    Activations Density 0.715%

    No Known Activations