© 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. 41-GEMMASCOPE-RES-16K
    11. 7186
    Prev
    Next
    INDEX
    Explanations

    specific combinations of alphanumeric characters or tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.45
     CanadaChoose
    -0.40
    AFX
    -0.39
    TokenNameDOT
    -0.36
     OP
    -0.35
    HXLINE
    -0.35
    ViewFeatures
    -0.34
    SequentialGroup
    -0.33
    MENAFN
    -0.33
    PROLOG
    -0.32
    POSITIVE LOGITS
     estekak
    0.51
    पया
    0.50
    gc
    0.47
    styleType
    0.46
    Aiheesta
    0.45
    Jc
    0.45
     sumpay
    0.45
    gg
    0.44
    Bc
    0.44
    Ec
    0.43
    Activations Density 0.332%

    No Known Activations