© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8150
    Prev
    Next
    INDEX
    Explanations

    punctuations and symbols in the text, indicating structural or formatting elements

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

    Code package/file paths

    np_acts-logits-general · gemini-2.0-flash

    . Appgamerx javatestfoundationfilecore

    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
     ready
    -0.30
    相
    -0.29
     than
    -0.28
     в
    -0.26
     put
    -0.26
     created
    -0.26
     cons
    -0.26
     as
    -0.25
     ini
    -0.25
     take
    -0.24
    POSITIVE LOGITS
    出版年
    0.82
    :✨
    0.82
    #+#
    0.81
    oa̍t
    0.81
    AndEndTag
    0.80
     للمعارف
    0.78
     ſes
    0.78
    <unused47>
    0.77
    <unused43>
    0.77
    <unused41>
    0.77
    Activations Density 0.127%

    No Known Activations