© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 10459
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical expressions, particularly those related to functions and sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -1.03
    存于互联网档案馆
    -0.96
     CreateTagHelper
    -0.87
    IntoConstraints
    -0.84
     JpaRepository
    -0.77
     autorytatywna
    -0.77
     PeEnEo
    -0.77
     queſta
    -0.76
    StoryboardSegue
    -0.76
     Administrativna
    -0.76
    POSITIVE LOGITS
     bocetos
    0.45
     calcetines
    0.39
     cejas
    0.36
    citos
    0.35
     Gubernur
    0.34
     botines
    0.34
    visející
    0.33
     short
    0.33
    jangkau
    0.32
     redacción
    0.32
    Activations Density 2.241%

    No Known Activations