© 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. 16-GEMMASCOPE-RES-16K
    11. 13846
    Prev
    Next
    INDEX
    Explanations

    actions related to forceful pushing or movement

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

    "push"

    np_acts-logits-general · gemini-2.0-flash

    pushing and being pushed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corações
    -0.57
     telinga
    -0.55
     Barkley
    -0.54
    listdir
    -0.53
     Kurtz
    -0.51
    ————————
    -0.49
     mater
    -0.49
    cein
    -0.48
     Coates
    -0.48
    Brains
    -0.47
    POSITIVE LOGITS
     push
    1.63
     pushes
    1.50
     PUSH
    1.48
     Push
    1.46
     Pushing
    1.43
     pushed
    1.42
     pusher
    1.42
     pushing
    1.42
    Pushing
    1.35
    pushed
    1.34
    Activations Density 0.079%

    No Known Activations