© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6174
    Prev
    Next
    INDEX
    Explanations

    words related to the action of "pushing” or similar motions and their context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "push" and its variations

    np_acts-logits-general · gemini-2.0-flash

    push

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    økt
    -0.54
     chauss
    -0.53
    listdir
    -0.52
    BASEPATH
    -0.50
    tulo
    -0.49
     Communities
    -0.49
     STC
    -0.48
     Barkley
    -0.48
    bereitung
    -0.47
     lateinit
    -0.47
    POSITIVE LOGITS
     push
    1.17
     Pushing
    1.14
     pushes
    1.13
     PUSH
    1.09
     pushed
    1.08
     pushing
    1.07
    Pushing
    1.04
     Push
    1.01
    pushed
    0.94
    push
    0.94
    Activations Density 0.052%

    No Known Activations