© 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. 11090
    Prev
    Next
    INDEX
    Explanations

    references to leadership and notable achievements in professional contexts

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

    Follows a number in a list

    np_acts-logits-general · gemini-2.0-flash

    number pairings and rankings

    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
     always
    -1.00
     Always
    -0.89
     siempre
    -0.88
    Always
    -0.87
    always
    -0.86
     תמיד
    -0.86
     всегда
    -0.82
    siempre
    -0.80
     zawsze
    -0.78
     Siempre
    -0.75
    POSITIVE LOGITS
     watch
    0.85
    watch
    0.81
     Watch
    0.79
    Watch
    0.72
     WATCH
    0.71
     future
    0.64
     Rising
    0.63
    future
    0.62
    Rising
    0.62
    WATCH
    0.61
    Activations Density 0.144%

    No Known Activations