© 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. 8183
    Prev
    Next
    INDEX
    Explanations

    questions and discussions about the feasibility or validity of certain concepts

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

    "Is it" or variants

    np_acts-logits-general · gemini-2.0-flash

    Is it possible

    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
    almost
    -0.84
     Sehr
    -0.78
    very
    -0.73
     almost
    -0.72
     very
    -0.70
    Almost
    -0.70
     VERY
    -0.69
     quase
    -0.68
    Very
    -0.65
     excellently
    -0.65
    POSITIVE LOGITS
     ever
    1.43
     jemals
    1.26
     any
    1.17
     überhaupt
    1.09
    ever
    1.03
     EVER
    1.02
     anything
    0.98
     siquiera
    0.95
     indeed
    0.94
     quelconque
    0.94
    Activations Density 0.700%

    No Known Activations