© 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. 20-GEMMASCOPE-RES-16K
    11. 8241
    Prev
    Next
    INDEX
    Explanations

    scientific procedures and experimental methodologies

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

    Following a methodological description

    np_acts-logits-general · gemini-2.0-flash

    briefly, initially, firstly, details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     even
    -0.57
     still
    -0.54
    ⓧ
    -0.53
     yet
    -0.52
     but
    -0.50
    But
    -0.49
     longtemps
    -0.47
    PerformLayout
    -0.47
     certainly
    -0.47
     zelfs
    -0.46
    POSITIVE LOGITS
     Briefly
    0.86
     ابتدا
    0.75
    まず
    0.74
     details
    0.74
     hierzu
    0.72
    Initially
    0.72
     firstly
    0.71
    intios
    0.71
    まずは
    0.71
     Firstly
    0.70
    Activations Density 1.384%

    No Known Activations