© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4239
    Prev
    Next
    INDEX
    Explanations

    phrases and verbs related to pushing, driving, or promoting action and ideas

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

    "push" or "pushing"

    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-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    الدراسه
    -0.47
     Wiktionnaire
    -0.43
     isComment
    -0.38
    basicConfig
    -0.35
     Bett
    -0.34
    fieldLabel
    -0.33
     ***!
    -0.33
    联网
    -0.31
    ynb
    -0.31
     qualidade
    -0.30
    POSITIVE LOGITS
     push
    1.44
    push
    1.34
     PUSH
    1.31
     pushes
    1.29
     Push
    1.29
     pushed
    1.23
    Push
    1.21
     pushing
    1.19
     Pushing
    1.18
    PUSH
    1.17
    Activations Density 0.151%

    No Known Activations