Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 3125
    Prev
    Next
    INDEX
    Explanations

    situations involving physical positions and rest

    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
     porte
    -0.46
    wpi
    -0.43
     poveznice
    -0.43
    mfrac
    -0.42
    thalam
    -0.42
    çage
    -0.41
    nellement
    -0.40
     poivre
    -0.39
    Entradas
    -0.39
    PyExc
    -0.38
    POSITIVE LOGITS
     chairs
    1.86
     chair
    1.84
     couch
    1.75
     seating
    1.71
     sofa
    1.66
     seat
    1.64
     seats
    1.64
     seated
    1.60
     CHAIR
    1.58
     sitting
    1.57
    Activations Density 0.212%

    No Known Activations