© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4141
    Prev
    Next
    INDEX
    Explanations

    references to historical events or timelines

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

    Time periods or durations

    np_acts-logits-general · gemini-2.0-flash

    years elapsed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     queſta
    -0.64
     itſelf
    -0.63
     $_(
    -0.62
    ⅘
    -0.61
    irvana
    -0.60
    <unused28>
    -0.60
    <unused74>
    -0.60
    <unused14>
    -0.60
    <pad>
    -0.60
    <unused3>
    -0.60
    POSITIVE LOGITS
     until
    0.61
     immediately
    0.42
     quickly
    0.42
    until
    0.41
     Until
    0.40
    その後
    0.39
     continued
    0.39
    Until
    0.38
     then
    0.38
     untill
    0.38
    Activations Density 0.517%

    No Known Activations