© 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. 3940
    Prev
    Next
    INDEX
    Explanations

    guidance or recommendations for problem-solving or decision-making

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

    Russian language or script

    np_acts-logits-general · gemini-2.0-flash

    Russian greetings and phrases

    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
     G
    -0.77
     I
    -0.77
     B
    -0.77
     T
    -0.77
     Y
    -0.75
     L
    -0.74
     
    -0.74
     pre
    -0.73
     F
    -0.73
     l
    -0.71
    POSITIVE LOGITS
     незавершена
    1.31
    GEBURTSDATUM
    1.23
    expandindo
    1.17
    ьаж
    1.12
    RectangleBorder
    1.11
     мәкал
    1.08
    цездатний
    1.05
    RenderAtEndOf
    1.05
     cherchés
    1.04
     AssemblyTitle
    1.03
    Activations Density 0.020%

    No Known Activations