© 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. 13776
    Prev
    Next
    INDEX
    Explanations

    discussions around size, measurement, and comparative analysis in various contexts

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

    Measurements or comparisons of size

    np_acts-logits-general · gemini-2.0-flash

    size and dimensions

    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
     trăm
    -0.37
    llingwood
    -0.36
    fillType
    -0.36
     vectorielle
    -0.35
    cticide
    -0.34
     Salve
    -0.34
     sisält
    -0.34
     kayna
    -0.34
     Sheen
    -0.34
    调
    -0.33
    POSITIVE LOGITS
     size
    1.09
     sizes
    0.98
     sized
    0.96
     Size
    0.94
     tamaño
    0.93
     Sizes
    0.90
    IntoConstraints
    0.86
    sized
    0.85
     taille
    0.85
    size
    0.85
    Activations Density 0.491%

    No Known Activations