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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9933
    Prev
    Next
    INDEX
    Explanations

    the concept of "push" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qrstuvwxyz
    -0.66
    getOptions
    -0.63
     spect
    -0.63
    mycompany
    -0.60
     portátil
    -0.60
     Verhältnisse
    -0.59
    cerna
    -0.59
    rüstung
    -0.58
    vener
    -0.58
    راتيج
    -0.57
    POSITIVE LOGITS
     push
    3.39
     Push
    3.07
     PUSH
    2.91
    push
    2.90
     pushes
    2.85
    Push
    2.83
     pushing
    2.81
     pushed
    2.77
     Pushing
    2.75
    Pushing
    2.61
    Activations Density 0.053%

    No Known Activations