© 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-2-9B
    7. Residual Stream - 16k
    9. 13-GEMMASCOPE-RES-16K
    11. 8151
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gustó
    -0.51
    writeFieldEnd
    -0.50
     podéis
    -0.48
    VersionUID
    -0.47
    存于互联网档案馆
    -0.45
     světě
    -0.43
     hicimos
    -0.43
     femenina
    -0.42
    rxjs
    -0.42
    ArgumentParser
    -0.42
    POSITIVE LOGITS
     T
    0.81
    T
    0.71
     TT
    0.66
     Tl
    0.64
    getT
    0.61
     Tc
    0.61
     t
    0.60
    TEntity
    0.60
     TG
    0.59
     TL
    0.59
    Activations Density 4.554%

    No Known Activations