© 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. 2-GEMMASCOPE-RES-16K
    11. 4826
    Prev
    Next
    INDEX
    Explanations

    phrases that convey physical states or actions, particularly those related to body movements and health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ècie
    -0.66
    Autoritní
    -0.65
    esteld
    -0.62
    #+#
    -0.62
     विश्वसनीयता
    -0.58
     TextAppearance
    -0.57
    ndice
    -0.57
    Vidite
    -0.54
    CloseOperation
    -0.53
     indisponible
    -0.52
    POSITIVE LOGITS
    ori
    0.55
    mula
    0.47
    Einzelnachweise
    0.47
    逐
    0.45
    ComponentModel
    0.45
    ere
    0.45
    ORI
    0.44
    kt
    0.44
    ION
    0.43
    ExecutionContext
    0.43
    Activations Density 1.951%

    No Known Activations