© 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. 1369
    Prev
    Next
    INDEX
    Explanations

    references to institutions or organizations in academic and professional contexts

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

    Followed by prepositions or possessives

    np_acts-logits-general · gemini-2.0-flash

    under Turkish inbox

    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
     Administrativna
    -0.79
    rungsseite
    -0.58
    Rhestr
    -0.54
    ParallelGroup
    -0.54
     autorytatywna
    -0.52
    yntaxException
    -0.51
     fieltro
    -0.49
    WithIOException
    -0.49
    ConstraintMaker
    -0.49
    tagHelperRunner
    -0.48
    POSITIVE LOGITS
    #
    0.45
    //
    0.43
    Autumn
    0.40
     Cuer
    0.38
    apuram
    0.38
     arşivlendi
    0.37
    burgo
    0.37
     okuyayım
    0.37
     vergeben
    0.37
    American
    0.36
    Activations Density 0.191%

    No Known Activations