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

    Neuronpedia

    Jacobian LensNEW
    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. 5934
    Prev
    Next
    INDEX
    Explanations

    instances of active and descriptive language, particularly in a narrative context

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

    ending in "ing", "ed", "gy", "ib" or "uff"

    np_acts-logits-general · gemini-2.0-flash

    wing / cked / ing

    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
    󠁴
    -0.52
    帖最后由
    -0.50
    endregion
    -0.49
     ویکی‌پدی
    -0.48
     myſelf
    -0.47
    arraycopy
    -0.47
    MathML
    -0.47
     ſtand
    -0.47
    WRENCE
    -0.46
    SPJ
    -0.46
    POSITIVE LOGITS
     squ
    0.39
    ocracy
    0.38
     chewing
    0.38
     giddy
    0.37
    érité
    0.36
     poised
    0.35
     ragged
    0.35
    toISOString
    0.35
     batting
    0.34
    fit
    0.34
    Activations Density 0.335%

    No Known Activations