© 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. 5766
    Prev
    Next
    INDEX
    Explanations

    discussions about balance or middle ground in situations

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

    a midpoint or middle position

    np_acts-logits-general · gemini-2.0-flash

    middle or intermediate

    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
    IntoConstraints
    -0.61
    RegistryLite
    -0.61
     Италијани
    -0.61
    IContainer
    -0.58
    esModule
    -0.58
     Wikimedijinoj
    -0.58
    Begriffsklä
    -0.57
     सत्यापित
    -0.56
    webElementXpaths
    -0.56
    rawDesc
    -0.54
    POSITIVE LOGITS
     middle
    2.88
    middle
    2.63
     mid
    2.57
    mid
    2.29
     MIDDLE
    2.20
    Middle
    2.19
     intermediate
    2.14
     Mid
    2.09
    Mid
    2.09
     Middle
    2.06
    Activations Density 0.391%

    No Known Activations