© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10632
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character 'C' in various contexts, possibly related to mathematical or coding expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.87
     Италијани
    -0.50
     juſ
    -0.50
     tranſ
    -0.46
     pleaſure
    -0.44
     purpoſe
    -0.44
    CloseOperation
    -0.43
     fubject
    -0.42
     RouterModule
    -0.42
     cauſe
    -0.42
    POSITIVE LOGITS
     برانيه
    0.57
     behulp
    0.55
    InputBorder
    0.53
     betrekking
    0.52
     zelve
    0.51
    AsUp
    0.50
    esserts
    0.49
    ГЛА
    0.48
     Händen
    0.48
     organisatie
    0.47
    Activations Density 1.199%

    No Known Activations