© 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. 10679
    Prev
    Next
    INDEX
    Explanations

    references to legal situations and actions

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

    Occurrences or actions happening "while" something else

    np_acts-logits-general · gemini-2.0-flash

    actions after objects

    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
    دانشنامهٔ
    -0.86
     Réponses
    -0.81
     gynhyrchwyd
    -0.77
    Literatuur
    -0.76
     sowieso
    -0.74
    Demografía
    -0.73
    RenderAtEndOf
    -0.71
     ohnehin
    -0.70
    raszam
    -0.70
     становника
    -0.68
    POSITIVE LOGITS
     accidentally
    0.67
     during
    0.64
     after
    0.62
     allegedly
    0.60
     mistakenly
    0.57
     dintr
    0.56
     while
    0.55
     disambiguazione
    0.55
     late
    0.53
     nadat
    0.52
    Activations Density 0.493%

    No Known Activations