© 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. 19-GEMMASCOPE-RES-16K
    11. 7449
    Prev
    Next
    INDEX
    Explanations

    statements about readiness and preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     konusu
    -0.49
    ulic
    -0.40
    つい
    -0.38
    ミア
    -0.38
     SDLK
    -0.37
    理石
    -0.37
    fal
    -0.36
    mittent
    -0.36
     cayó
    -0.36
    lain
    -0.35
    POSITIVE LOGITS
     ready
    2.94
     readiness
    2.67
     Ready
    2.56
    ready
    2.54
     preparation
    2.50
     prepared
    2.48
     READY
    2.45
    Ready
    2.37
     prepare
    2.35
     Preparation
    2.27
    Activations Density 0.339%

    No Known Activations