© 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. 16-GEMMASCOPE-RES-16K
    11. 7916
    Prev
    Next
    INDEX
    Explanations

    concepts related to comparison and analysis in various contexts

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

    preceding "of" or "to"

    np_acts-logits-general · gemini-2.0-flash

    analysis of concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poffible
    -0.73
    ötzlich
    -0.69
     censiti
    -0.66
     kollu
    -0.66
     beſt
    -0.65
    GEBURTSDATUM
    -0.64
     disambiguazione
    -0.63
    复制代码
    -0.63
    bibinfo
    -0.63
    smöglichkeiten
    -0.62
    POSITIVE LOGITS
     that
    0.57
     standpoint
    0.56
    tagext
    0.54
    EJB
    0.52
     consisting
    0.48
     namens
    0.48
     versehen
    0.48
     based
    0.48
    mainAxisSize
    0.47
     paio
    0.47
    Activations Density 1.473%

    No Known Activations