© 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. 2993
    Prev
    Next
    INDEX
    Explanations

    names of people, specifically in the context of news articles

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

    Indian first names

    np_acts-logits-general · gemini-2.0-flash

    Indian names

    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
    ungeon
    -0.54
     therefore
    -0.52
    republik
    -0.51
    rillation
    -0.50
    Encyclo
    -0.50
     valign
    -0.49
     accordingly
    -0.48
     consequently
    -0.48
    ebbe
    -0.48
    τον
    -0.48
    POSITIVE LOGITS
    deep
    0.71
    ValueStyle
    0.70
    OGND
    0.69
     kasarigan
    0.69
    Kumar
    0.65
     Kumar
    0.60
    WebElementEntity
    0.60
    jeet
    0.60
    LookAnd
    0.60
     kumar
    0.60
    Activations Density 0.129%

    No Known Activations