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

    Neuronpedia

    Jacobian LensNEW
    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. 8619
    Prev
    Next
    INDEX
    Explanations

    repeated references to the concept of "back"

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

    Directional words like "up," "down," or "back."

    np_acts-logits-general · gemini-2.0-flash

    back then

    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
     Monfieur
    -1.19
     itſelf
    -1.07
     Jefus
    -1.07
     myſelf
    -1.04
     pleaſure
    -1.04
     houſe
    -1.02
     Efq
    -1.01
     ſta
    -1.01
     Diſ
    -1.00
     himſelf
    -1.00
    POSITIVE LOGITS
     around
    0.67
     in
    0.65
     up
    0.63
     down
    0.61
     toward
    0.59
     at
    0.58
     out
    0.58
     towards
    0.56
     along
    0.56
     on
    0.52
    Activations Density 0.123%

    No Known Activations