© 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. 8730
    Prev
    Next
    INDEX
    Explanations

    expressions indicating personal opinions or subjective statements

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

    Follows commas and certain conjunctions

    np_acts-logits-general · gemini-2.0-flash

    punctuation followed by new context

    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
    Exhibit
    -0.38
    aryng
    -0.38
    İstinadlar
    -0.36
    richting
    -0.35
    љено
    -0.35
     zás
    -0.35
     LTS
    -0.35
    efois
    -0.35
    niająca
    -0.35
     Enter
    -0.34
    POSITIVE LOGITS
    ########.
    0.59
    makeConstraints
    0.51
     Administrativna
    0.49
     OFDb
    0.47
    inSlope
    0.46
    WithIOException
    0.46
    NSYLVANIA
    0.43
     planche
    0.42
    writerow
    0.41
    styleable
    0.41
    Activations Density 0.179%

    No Known Activations