© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    high-activity indicators related to a specific subject or condition

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

    Characters commonly used in code or math expressions

    np_acts-logits-general · gemini-2.0-flash

    bracketed numbers and symbols

    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
     HttpNotFound
    -0.93
     AssemblyCulture
    -0.89
     مشين
    -0.89
     EconPapers
    -0.87
     مرئيه
    -0.86
     linkovi
    -0.79
    PerformLayout
    -0.75
     Wicidata
    -0.73
     ModelExpression
    -0.71
     calendriers
    -0.69
    POSITIVE LOGITS
     vård
    0.52
     médicaux
    0.51
     săptăm
    0.48
     ajudá
    0.46
     certiorari
    0.46
     wijze
    0.45
     indipendente
    0.45
    IsInitialized
    0.45
     inútil
    0.45
     disposent
    0.44
    Activations Density 0.161%

    No Known Activations