Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8262
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "I don’t" and its variations

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

    Punctuation, especially apostrophes or brackets

    np_acts-logits-general · gemini-2.0-flash

    legal separation or computing terms

    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
     
    -0.65
     (
    -0.60
     and
    -0.52
     [
    -0.50
     or
    -0.49
    _
    -0.45
     &
    -0.44
     The
    -0.44
    /
    -0.44
     /
    -0.43
    POSITIVE LOGITS
     imagui
    0.98
     Geiſt
    0.98
     verſch
    0.97
    niſſe
    0.97
     beſch
    0.97
     increí
    0.96
     zwiſchen
    0.95
     queſta
    0.95
     Administrativna
    0.95
     Weiſe
    0.94
    Activations Density 0.651%

    No Known Activations