© 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. 22-GEMMASCOPE-RES-16K
    11. 9038
    Prev
    Next
    INDEX
    Explanations

    food items and ingredients referenced within culinary contexts

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

    Follows abbreviations of cheese types

    np_acts-logits-general · gemini-2.0-flash

    food items and ingredients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pragma
    -0.57
     sekali
    -0.56
     CascadeType
    -0.54
    istisches
    -0.53
    Bibliografía
    -0.53
    vertical
    -0.51
    ukone
    -0.51
     devrez
    -0.51
     Ketten
    -0.50
     const
    -0.50
    POSITIVE LOGITS
    Datuak
    0.58
     😋
    0.53
    DeleteBehavior
    0.53
    AnchorStyles
    0.52
    gameserver
    0.52
     fraî
    0.51
     Arro
    0.49
     Yuc
    0.49
     caes
    0.48
    +#+#
    0.48
    Activations Density 0.151%

    No Known Activations