© 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. 10584
    Prev
    Next
    INDEX
    Explanations

    instances of the word "variety" and related concepts indicating diversity or multiple types

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

    "variety of"

    np_acts-logits-general · gemini-2.0-flash

    variety of

    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
     Audiodateien
    -0.56
    VARIABLE
    -0.51
    cored
    -0.47
    izzard
    -0.46
    machte
    -0.45
    riebene
    -0.44
    ICIENCY
    -0.44
    valbard
    -0.44
    becher
    -0.42
    voerd
    -0.42
    POSITIVE LOGITS
     genres
    0.79
     assortment
    0.74
     flavors
    0.71
     plais
    0.71
     backgrounds
    0.69
     textures
    0.68
     ways
    0.68
    各样的
    0.68
    windowFixed
    0.68
     afield
    0.68
    Activations Density 0.137%

    No Known Activations