© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 9360
    Prev
    Next
    INDEX
    Explanations

    elements related to web page structure and data representation, particularly in the context of listings like players in a league or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.48
     onPostExecute
    -0.45
    ########.
    -0.44
     iParam
    -0.41
    IsMutable
    -0.39
     transmission
    -0.38
     poème
    -0.38
    Šaltiniai
    -0.38
     zas
    -0.38
     bParam
    -0.37
    POSITIVE LOGITS
     مشين
    0.70
    Personendaten
    0.60
    {{
    0.59
    webElementXpaths
    0.59
     league
    0.57
     leading
    0.56
     EUROPEAN
    0.55
     leagues
    0.55
     LEAGUE
    0.55
    league
    0.53
    Activations Density 0.222%

    No Known Activations