Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 12254
    Prev
    Next
    INDEX
    Explanations

    technical terms and methods related to materials characterization and analysis

    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
    PerformLayout
    -0.66
    ArgumentParser
    -0.65
     Scalars
    -0.61
    TintMode
    -0.58
    IsMutable
    -0.57
     FormGroup
    -0.57
    ostoma
    -0.54
    DispatchToProps
    -0.54
    ädie
    -0.53
     chef
    -0.53
    POSITIVE LOGITS
    DrawerToggle
    0.68
     diffraction
    0.55
     powder
    0.54
     kır
    0.53
     dif
    0.53
     X
    0.52
     recaud
    0.52
    RIX
    0.52
     XRD
    0.51
    Dif
    0.49
    Activations Density 0.710%

    No Known Activations