© 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. 24-GEMMASCOPE-RES-16K
    11. 4203
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific identifiers

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

    Non-English words

    np_acts-logits-general · gemini-2.0-flash

    Malay, Dutch, Turkish, Islamic, English names, programming code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.77
    CodeAttribute
    -0.71
    RectangleBorder
    -0.63
     MainAxisSize
    -0.61
    ArrowToggle
    -0.57
     CURIAM
    -0.55
    addCriterion
    -0.55
     onItemClick
    -0.53
     TestBed
    -0.53
    RetentionPolicy
    -0.53
    POSITIVE LOGITS
     vielen
    0.59
     zat
    0.58
     deed
    0.57
     leid
    0.56
    TypedDataSet
    0.55
     word
    0.54
     heeft
    0.53
     viel
    0.52
     conclude
    0.52
     kon
    0.51
    Activations Density 0.061%

    No Known Activations