© 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. 21-GEMMASCOPE-RES-16K
    11. 14471
    Prev
    Next
    INDEX
    Explanations

    phrases detailing comparisons or expressing a range of options and interpretations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilis
    -0.45
    sez
    -0.44
    ophers
    -0.43
    ford
    -0.41
    none
    -0.40
    rans
    -0.38
    None
    -0.38
    bil
    -0.37
    eml
    -0.37
    maksud
    -0.37
    POSITIVE LOGITS
     thing
    3.59
     things
    2.88
     THING
    2.79
    thing
    2.79
     Thing
    2.55
    things
    2.49
    Thing
    2.45
     Things
    2.43
     THINGS
    2.38
    Things
    2.37
    Activations Density 0.343%

    No Known Activations