© 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. 8504
    Prev
    Next
    INDEX
    Explanations

    phrases that express excessive qualities or criticisms of size, weight, or convenience

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

    "too"

    np_acts-logits-general · gemini-2.0-flash

    excessive or unreasonable

    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
     cherchés
    -0.50
    phazard
    -0.48
    хьтан
    -0.48
    ésultat
    -0.47
    calciatore
    -0.47
    akim
    -0.47
    ində
    -0.46
    Portály
    -0.45
    assertNotNull
    -0.45
     getItemId
    -0.45
    POSITIVE LOGITS
     too
    3.44
    Too
    3.17
     Too
    3.13
    too
    3.09
     TOO
    2.90
    TOO
    2.47
     terlalu
    2.44
     demasiado
    2.42
     troppo
    2.38
     слишком
    2.36
    Activations Density 0.518%

    No Known Activations