© 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. 1272
    Prev
    Next
    INDEX
    Explanations

    theoretical references and hypotheses in scientific discussions

    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
    wness
    -0.66
    <()>
    -0.56
     Glan
    -0.53
     שוליים
    -0.52
    antMatchers
    -0.51
     SPSS
    -0.50
    adple
    -0.49
     חיצוניים
    -0.49
    êncio
    -0.49
    zeera
    -0.49
    POSITIVE LOGITS
     theory
    1.92
     theories
    1.71
    theory
    1.59
     Theory
    1.53
     hypothesis
    1.47
    Theory
    1.47
     THEORY
    1.38
     théorie
    1.31
     Theories
    1.31
     hypotheses
    1.30
    Activations Density 0.876%

    No Known Activations