© 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. 11401
    Prev
    Next
    INDEX
    Explanations

    words related to significant concepts of judgment and morality

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

    Follows the article "a"

    np_acts-logits-general · gemini-2.0-flash

    'a' followed by state, suicidal, more, nod, lot, bit, year, show, cert

    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
     ostavi
    -0.60
    DataSnapshot
    -0.59
    complexContent
    -0.55
    ComponentScan
    -0.54
    ScopeManager
    -0.53
     pinulongan
    -0.53
    ÍTULO
    -0.52
     above
    -0.51
    ultur
    -0.50
    ouncements
    -0.49
    POSITIVE LOGITS
    ttää
    0.53
    webElementGuid
    0.51
     edelstahl
    0.48
    htë
    0.47
    robat
    0.47
     gewi
    0.45
    sweise
    0.45
    erweise
    0.44
     Aces
    0.44
    crunch
    0.43
    Activations Density 0.066%

    No Known Activations