© 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. 28-GEMMASCOPE-RES-16K
    11. 8509
    Prev
    Next
    INDEX
    Explanations

    declarative sentences with significant verbs and indicators of existence or state

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

    Comes after a form of the word "is" or "are"

    np_acts-logits-general · gemini-2.0-flash

    state descriptions

    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
    ResponseWriter
    -0.58
     utafitiHapana
    -0.50
     Cæsar
    -0.50
    ftagPool
    -0.48
    fjspx
    -0.48
    WithIOException
    -0.47
    ۗ
    -0.47
     iprot
    -0.46
     مرئيه
    -0.45
     المعيارى
    -0.43
    POSITIVE LOGITS
    httphttps
    0.47
     numberOfRows
    0.44
    vieran
    0.43
    Бахар
    0.40
    bildēt
    0.40
    務
    0.37
    実は
    0.37
    ViewFeatures
    0.37
     itself
    0.37
     Leck
    0.36
    Activations Density 1.205%

    No Known Activations