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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14377
    Prev
    Next
    INDEX
    Explanations

    references to character encoding formats, particularly UTF-8

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

    "utf-8" encoding declaration

    np_acts-logits-general · gemini-2.0-flash

    utf-8 encoding

    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
    OpenHelper
    -0.82
    ArgumentParser
    -0.76
    MeasureSpec
    -0.74
    tonsoft
    -0.72
    protoimpl
    -0.72
    sidemargin
    -0.72
    apimachinery
    -0.71
     متعلقه
    -0.68
     Italijani
    -0.68
     Administrativna
    -0.67
    POSITIVE LOGITS
    8
    0.59
     érz
    0.43
    GraphicsUnit
    0.43
     internal
    0.42
    Preconditions
    0.42
    LEAD
    0.41
    least
    0.40
    magic
    0.40
    internal
    0.40
    cree
    0.39
    Activations Density 0.094%

    No Known Activations