© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3685
    Prev
    Next
    INDEX
    Explanations

    contexts involving movement or passage through spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clientWidth
    -0.51
    lardır
    -0.46
    jard
    -0.43
     Fabri
    -0.43
     Reiz
    -0.42
     Mak
    -0.42
     konu
    -0.41
    enz
    -0.41
     måde
    -0.40
    Mak
    -0.39
    POSITIVE LOGITS
    THROUGH
    1.55
    through
    1.50
    Through
    1.42
     THROUGH
    1.38
     through
    1.37
     Through
    1.36
     thru
    1.19
     Thru
    1.18
     thro
    1.11
    Thru
    1.09
    Activations Density 0.126%

    No Known Activations