© 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. 18-GEMMASCOPE-RES-16K
    11. 400
    Prev
    Next
    INDEX
    Explanations

    references to responsibilities and roles within a religious or community context

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

    Prepositions

    np_acts-logits-general · gemini-2.0-flash

    prepositions introducing nouns or clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.88
     myſelf
    -0.87
     impactful
    -0.84
     Jefus
    -0.83
     Efq
    -0.81
     incentiv
    -0.79
     Majefty
    -0.79
     himſelf
    -0.79
     alfo
    -0.78
     Chrift
    -0.77
    POSITIVE LOGITS
     daß
    0.80
     muß
    0.76
     Meksiku
    0.65
     Himo
    0.64
     mußte
    0.63
     läßt
    0.61
     skall
    0.60
     wußte
    0.58
    faßt
    0.56
     mußten
    0.54
    Activations Density 0.830%

    No Known Activations