© 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. 3664
    Prev
    Next
    INDEX
    Explanations

    variances in context and structure, particularly in the formulation of questions and contrasting statements

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

    Punctuation followed by question words

    np_acts-logits-general · gemini-2.0-flash

    punctuation before questions

    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
    uegos
    -0.33
    XmlAccessorType
    -0.33
     ffilm
    -0.32
    FlatAppearance
    -0.31
     oprot
    -0.31
     <<<<<<<<<<<<<<
    -0.31
    DIPSETTING
    -0.30
    endregion
    -0.30
    ernalia
    -0.29
    fieras
    -0.29
    POSITIVE LOGITS
     how
    1.96
     what
    1.75
    How
    1.58
     How
    1.54
    What
    1.47
     why
    1.45
     What
    1.43
    how
    1.41
    what
    1.38
     cómo
    1.36
    Activations Density 1.608%

    No Known Activations