© 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. 22-GEMMASCOPE-RES-16K
    11. 10589
    Prev
    Next
    INDEX
    Explanations

    indications of concern or discussions about safety-related issues

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

    followed by personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    expressing uncertainty or preference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poichè
    -0.82
     ainfi
    -0.80
     !)
    -0.75
    깥
    -0.75
     feroit
    -0.73
     serupa
    -0.73
     آنان
    -0.72
     således
    -0.72
    已是
    -0.70
    几人
    -0.70
    POSITIVE LOGITS
     somebody
    1.20
     everybody
    1.12
     really
    1.11
     maybe
    1.05
    somebody
    1.01
     anybody
    1.00
     sort
    0.99
     [
    0.97
     basically
    0.97
     kind
    0.95
    Activations Density 0.320%

    No Known Activations