© 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. 12453
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to automotive features and aesthetics

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

    Follows a subjective opinion

    np_acts-logits-general · gemini-2.0-flash

    adds elegance visually

    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
    HtmlAttribute
    -0.64
    ikala
    -0.55
    archiviato
    -0.52
    lably
    -0.52
    IsContent
    -0.51
    LookAnd
    -0.51
     onBind
    -0.49
    zám
    -0.49
     reformed
    -0.49
    opardy
    -0.49
    POSITIVE LOGITS
     complement
    1.32
     complements
    1.19
     compliment
    1.18
     adds
    1.17
    Complement
    1.16
     Complement
    1.13
    complement
    1.11
     add
    1.06
     complé
    1.03
     compliments
    0.99
    Activations Density 0.199%

    No Known Activations