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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 11778
    Prev
    Next
    INDEX
    Explanations

    references to varying conditions or contexts in different studies or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
    QMetaType
    -0.75
    ReusableCell
    -0.73
    ^(@)
    -0.68
    rungsseite
    -0.68
    出版年
    -0.66
     itſelf
    -0.63
     religione
    -0.63
    Datasets
    -0.60
     TextInputType
    -0.60
    DetailComponent
    -0.60
    POSITIVE LOGITS
     places
    1.13
     locations
    0.94
     parts
    0.89
     times
    0.86
     occasions
    0.86
    places
    0.83
     moments
    0.80
    Places
    0.80
     lugares
    0.80
     Places
    0.78
    Activations Density 0.488%

    No Known Activations