© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 818
    Prev
    Next
    INDEX
    Explanations

    references to articles and descriptors in various contexts

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

    Follows the indefinite article "a"

    np_acts-logits-general · gemini-2.0-flash

    a particular

    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
    <bos>
    -0.57
     trúc
    -0.49
     szint
    -0.49
    AddHtmlAttribute
    -0.48
    なんと
    -0.47
    FunctionFlags
    -0.47
     eget
    -0.45
     instead
    -0.44
     supplémentaire
    -0.44
     noget
    -0.44
    POSITIVE LOGITS
     given
    1.01
    iconque
    0.88
    given
    0.87
    hver
    0.82
     person
    0.80
     particular
    0.80
    StoryboardSegue
    0.80
     adott
    0.79
    Geplaatst
    0.79
     determinado
    0.76
    Activations Density 0.499%

    No Known Activations