© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6136
    Prev
    Next
    INDEX
    Explanations

    references to cellular processes and immune response mechanisms

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

    after "of" and describing cells

    np_acts-logits-general · gemini-2.0-flash

    infected cells

    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
     >=",
    -0.56
    tonsoft
    -0.55
     createState
    -0.52
     Strangers
    -0.51
    SceneManagement
    -0.51
    [::-
    -0.51
    %)$
    -0.50
    ResumeLayout
    -0.50
     recevez
    -0.49
     Amigos
    -0.48
    POSITIVE LOGITS
     cells
    1.57
    cells
    1.20
     Cells
    1.16
     cellules
    1.09
     CELLS
    1.06
    ocytes
    1.03
    Cells
    1.03
     neurons
    0.97
    zellen
    0.92
    cytes
    0.91
    Activations Density 1.326%

    No Known Activations