© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-GEMMASCOPE-RES-16K
    11. 1370
    Prev
    Next
    INDEX
    Explanations

    phrases that involve taking action or movement, particularly the verb "push" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.62
    getOptions
    -0.58
    boh
    -0.55
    qrstuvwxyz
    -0.54
    riwal
    -0.53
     Αυ
    -0.52
    ிரு
    -0.52
     spect
    -0.52
     αὐ
    -0.50
    runOnUiThread
    -0.50
    POSITIVE LOGITS
     push
    2.24
     pushed
    2.12
     pushes
    2.07
     pushing
    2.07
     Pushing
    2.06
    pushed
    2.01
    Pushing
    1.93
     Push
    1.92
     PUSH
    1.83
    Push
    1.67
    Activations Density 0.080%

    No Known Activations