Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7863
    Prev
    Next
    INDEX
    Explanations

    numerical data, particularly related to statistics and measurements

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

    Numbers followed by a unit of measurement or reference

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Handeln
    -0.46
     Gegenteil
    -0.44
     trhu
    -0.44
     powinien
    -0.43
     hovor
    -0.43
     zask
    -0.42
     llamaba
    -0.42
     Gefühle
    -0.42
     Ausgang
    -0.42
    contrar
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.81
    expandindo
    0.71
     Paglinawan
    0.61
     utafitiHapana
    0.57
    tableFuture
    0.55
    contentLoaded
    0.54
    awtextra
    0.53
     contextLoads
    0.53
    GEBURTSDATUM
    0.53
     wireType
    0.50
    Activations Density 0.859%

    No Known Activations