© 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-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10402
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of specific character names in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Maid
    -0.49
    getCmp
    -0.47
     ferons
    -0.47
    ゆる
    -0.47
    ijk
    -0.46
    SetData
    -0.45
    ст
    -0.45
    мети
    -0.45
    ztat
    -0.45
    ext
    -0.45
    POSITIVE LOGITS
    ou
    1.74
    OU
    1.51
    Ou
    1.37
    tou
    1.34
    Tou
    1.21
    oul
    1.18
     Ou
    1.16
     resourceCulture
    1.15
    kou
    1.10
    tvguidetime
    1.10
    Activations Density 0.037%

    No Known Activations