© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12140
    Prev
    Next
    INDEX
    Explanations

    references to significant historical events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     CreateTagHelper
    -0.68
     مشين
    -0.66
    aarrggbb
    -0.61
     arşivlendi
    -0.54
    tagHelperRunner
    -0.50
     temporales
    -0.49
     comuniques
    -0.48
    الدراسه
    -0.47
     personnal
    -0.47
     Palest
    -0.46
    POSITIVE LOGITS
    蚪
    0.42
    tagHelper
    0.41
     Zing
    0.39
     gom
    0.36
    得
    0.35
     Shorter
    0.35
     Plots
    0.35
    homonymie
    0.34
     Thumb
    0.34
     ngo
    0.34
    Activations Density 0.132%

    No Known Activations