© 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. 11933
    Prev
    Next
    INDEX
    Explanations

    the presence of the beginning of paragraphs or sections in a structured document

    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
    mathrm
    -0.40
    toner
    -0.37
    ’
    -0.36
    testify
    -0.35
    sear
    -0.34
    '
    -0.34
     ory
    -0.34
    mentor
    -0.33
    begin
    -0.33
     Track
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    1.01
     autorytatywna
    0.96
     Савезне
    0.93
    adaptiveStyles
    0.84
    AddTagHelper
    0.82
     ویکی‌پدی
    0.81
     Италијани
    0.80
    Personensuche
    0.79
    PreferredItem
    0.77
     defaultstate
    0.77
    Activations Density 0.000%

    No Known Activations