© 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. 8107
    Prev
    Next
    INDEX
    Explanations

    the presence of specific named references or identifiers in scientific literature

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

    Single letters followed by a period

    np_acts-logits-general · gemini-2.0-flash

    academic citations initials

    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
    enderror
    -0.68
    chemy
    -0.60
    
    -0.60
    ﮈ
    -0.59
    findpost
    -0.59
    linawan
    -0.59
    VIAF
    -0.58
    ݮ
    -0.57
    ſammen
    -0.57
    剽
    -0.57
    POSITIVE LOGITS
     setEmail
    0.34
     informée
    0.30
     aDecoder
    0.28
     M
    0.27
     C
    0.27
    ंदीखरीदारी
    0.26
     J
    0.26
     ***!
    0.26
     {?}
    0.26
     SearchView
    0.26
    Activations Density 0.081%

    No Known Activations