© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11296
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations and organizations

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

    Country or location names

    np_acts-logits-general · gemini-2.0-flash

    countries, cities, and states

    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
    enderror
    -0.80
    providedIn
    -0.77
    GEBURTSDATUM
    -0.65
    ParallelGroup
    -0.59
    )++;
    -0.59
    AnchorTagHelper
    -0.58
     ThemeData
    -0.56
     CreateTagHelper
    -0.55
    writeFieldEnd
    -0.53
    isContained
    -0.53
    POSITIVE LOGITS
    那边
    0.63
     Normdatei
    0.62
     Allí
    0.57
    あたり
    0.55
    tonode
    0.55
    เพื่อน
    0.54
    astrar
    0.52
     whither
    0.51
     COUNTRIES
    0.50
     wildfires
    0.50
    Activations Density 0.288%

    No Known Activations