© 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. 4-GEMMASCOPE-RES-16K
    11. 856
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to approvals and authorizations

    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
     
    -0.63
     k
    -0.63
    ing
    -0.62
     e
    -0.58
    ae
    -0.58
     K
    -0.55
     kaz
    -0.55
     I
    -0.55
     tra
    -0.55
     ph
    -0.54
    POSITIVE LOGITS
     approval
    2.25
     approved
    2.22
     Approval
    2.22
     approve
    2.17
     approvals
    2.15
     approves
    2.09
     approving
    2.04
     APPROVED
    2.03
     APPROVAL
    2.03
     Approved
    2.03
    Activations Density 0.092%

    No Known Activations