© 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. 20-GEMMASCOPE-RES-16K
    11. 3399
    Prev
    Next
    INDEX
    Explanations

    elements related to modifying and customizing content or experiences

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

    preceding "however," "whatever," "whichever," or "wherever"

    np_acts-logits-general · gemini-2.0-flash

    however, whatever, or, apart

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arid
    -0.60
    ChildScrollView
    -0.55
    ":["
    -0.50
    indro
    -0.45
    جوايز
    -0.44
    eld
    -0.43
     Juga
    -0.41
    casian
    -0.41
    γγ
    -0.41
    Hochspringen
    -0.41
    POSITIVE LOGITS
     however
    2.22
     whatever
    1.91
    however
    1.88
    whatever
    1.60
     whichever
    1.55
     wherever
    1.43
     Whatever
    1.42
    However
    1.41
    Whatever
    1.40
     However
    1.40
    Activations Density 0.315%

    No Known Activations