© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 699
    Prev
    Next
    INDEX
    Explanations

    words related to stepping or movement

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

    references to actions involving stepping or moving forward

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

    stepping into or out of situations

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     EconPapers
    -0.73
    MarshalTo
    -0.59
     Pública
    -0.56
    IUrlHelper
    -0.55
     링크
    -0.55
    blica
    -0.54
    LayoutConstraint
    -0.53
     <=",
    -0.53
    ))){
    -0.52
     sphinct
    -0.51
    POSITIVE LOGITS
     foot
    0.85
    Stepping
    0.80
     Stepping
    0.80
     stepping
    0.73
     stepped
    0.69
     aside
    0.69
     footsteps
    0.61
    Steps
    0.60
    Bronnen
    0.59
     foots
    0.58
    Activations Density 0.008%

    No Known Activations