© 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. 40-GEMMASCOPE-RES-16K
    11. 6320
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seperate
    -0.60
     seper
    -0.47
    Aholisi
    -0.47
     atleast
    -0.47
     disambiguazione
    -0.47
    enovo
    -0.44
    initialise
    -0.43
     Various
    -0.42
     Administrativna
    -0.42
     الحره
    -0.42
    POSITIVE LOGITS
     frecu
    0.69
     proy
    0.67
     viceversa
    0.64
     adecu
    0.64
     lineal
    0.64
     contemplates
    0.64
    proy
    0.64
     jajaja
    0.61
    specially
    0.58
     circun
    0.58
    Activations Density 1.189%

    No Known Activations