© 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. 22-GEMMASCOPE-RES-16K
    11. 5588
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to genetic and biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Abbreviations, especially acronyms in parentheses

    np_acts-logits-general · gemini-2.0-flash

    acronyms and initialisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.57
     purpoſe
    -0.56
     Koro
    -0.55
     Vira
    -0.54
     reaſon
    -0.53
     houſe
    -0.53
    KEYCODE
    -0.53
     Houſe
    -0.52
     TextInputType
    -0.52
     pleaſure
    -0.52
    POSITIVE LOGITS
     GF
    1.17
    CF
    1.13
    GF
    1.13
     DF
    1.13
    DF
    1.12
     CF
    1.12
    LF
    1.09
     Af
    1.09
     Raf
    1.08
    TF
    1.08
    Activations Density 0.913%

    No Known Activations