© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 1835
    Prev
    Next
    INDEX
    Explanations

    definitions and properties of programming functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.51
     myſelf
    -1.45
     itſelf
    -1.33
     doubtnut
    -1.32
     ་་
    -1.24
     Theſe
    -1.24
     Majefty
    -1.23
     themſelves
    -1.22
     Jefus
    -1.22
    ſelf
    -1.22
    POSITIVE LOGITS
      
    0.76
     OR
    0.66
     to
    0.65
     a
    0.64
     for
    0.64
     H
    0.64
     the
    0.63
     `
    0.62
     di
    0.62
     C
    0.61
    Activations Density 0.102%

    No Known Activations