© 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. 690
    Prev
    Next
    INDEX
    Explanations

    names or variations of the name "Ara."

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

    starting with "Ara" or "ra"

    np_acts-logits-general · gemini-2.0-flash

    Arrabellas and Araki/Ayars

    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
    참고
    -0.65
    gill
    -0.63
    н
    -0.61
    //
    -0.58
    gó
    -0.57
    gis
    -0.51
    g
    -0.50
    gens
    -0.48
    gum
    -0.48
    gent
    -0.47
    POSITIVE LOGITS
     Exacts
    0.65
    so
    0.61
     hObject
    0.61
    RuleContext
    0.59
     MonoBehaviour
    0.59
    SourceChecksum
    0.58
    IntoConstraints
    0.58
    FieldNumber
    0.58
    forChild
    0.56
    VIAF
    0.56
    Activations Density 0.175%

    No Known Activations