© 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. 24-GEMMASCOPE-RES-16K
    11. 14314
    Prev
    Next
    INDEX
    Explanations

    references to control and settings within a system

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

    Following tokens related to "finisher."

    np_acts-logits-general · gemini-2.0-flash

    finish or finisher moves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ScopeManager
    -0.83
     المعيارى
    -0.66
    PMailer
    -0.58
     MNRAS
    -0.55
    MLLoader
    -0.53
    BeginContext
    -0.52
    fgaben
    -0.52
    ClientRect
    -0.51
     /\.
    -0.50
     integrand
    -0.49
    POSITIVE LOGITS
     inputs
    0.71
     Inputs
    0.70
     AssemblyCulture
    0.64
     Street
    0.62
    Street
    0.61
     input
    0.61
     combos
    0.60
    Inputs
    0.60
     strings
    0.59
     bair
    0.58
    Activations Density 0.094%

    No Known Activations