© 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. 28-GEMMASCOPE-RES-16K
    6. 7660
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical values

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

    The numeral "1"

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers and symbols

    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
     betweenstory
    -0.79
     kasarigan
    -0.73
    webElementXpaths
    -0.73
    httphttps
    -0.68
    TagMode
    -0.68
    Personendaten
    -0.67
     للمعارف
    -0.67
     resourceCulture
    -0.66
     كومونز
    -0.66
    ../../
    -0.66
    POSITIVE LOGITS
    1
    0.85
    st
    0.51
    in
    0.35
    l
    0.31
    1
    0.31
    il
    0.29
     jurídico
    0.29
    १
    0.29
    lic
    0.27
    ′
    0.27
    Activations Density 1.447%

    No Known Activations