© 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. 1649
    Prev
    Next
    INDEX
    Explanations

    entities that identify organizations or businesses

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

    "is" followed by "a" or "as"

    np_acts-logits-general · gemini-2.0-flash

    is a/an/the

    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
     nakalista
    -0.82
     betweenstory
    -0.71
    Rüyada
    -0.71
     suivante
    -0.68
     untitled
    -0.68
    下手
    -0.64
    niająca
    -0.64
     suivants
    -0.63
    CompilerServices
    -0.63
     kaynağından
    -0.62
    POSITIVE LOGITS
    endregion
    0.58
     the
    0.58
     an
    0.56
     سكانية
    0.53
     a
    0.51
     unique
    0.50
     kind
    0.49
     committed
    0.49
     unknownFields
    0.49
     proud
    0.48
    Activations Density 0.195%

    No Known Activations