© 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. 24-GEMMASCOPE-RES-16K
    11. 4679
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific syntactical separators in text

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

    Commas followed by conjunctions/prepositions

    np_acts-logits-general · gemini-2.0-flash

    conjunctions after comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.61
     препратки
    -0.57
    Спољашње
    -0.55
    transQ
    -0.52
    ſelben
    -0.52
    guantes
    -0.52
    tafogo
    -0.52
     geſch
    -0.51
     wikipagina
    -0.51
    始化
    -0.50
    POSITIVE LOGITS
    routeProvider
    0.48
    ruik
    0.46
    FunctionFlags
    0.41
     As
    0.39
     Saltar
    0.38
    ,
    0.37
     společ
    0.36
    As
    0.35
     во
    0.35
    .,
    0.33
    Activations Density 0.151%

    No Known Activations