© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 1906
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to genetics and regulatory mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nø
    -0.48
     
    -0.38
    င
    -0.34
     in
    -0.33
    <eos>
    -0.32
     un
    -0.32
    an
    -0.31
    ad
    -0.31
     kesk
    -0.31
    in
    -0.31
    POSITIVE LOGITS
     Biôgrafia
    0.79
    InitVars
    0.75
    linawan
    0.68
    SourceChecksum
    0.67
     queſta
    0.66
    ſammen
    0.64
     noDo
    0.63
    Autoritní
    0.63
    afficheront
    0.62
    +#+#
    0.60
    Activations Density 2.417%

    No Known Activations