© 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. 13610
    Prev
    Next
    INDEX
    Explanations

    references to specific CD markers and their associated characteristics or effects

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

    "CD" followed by a number

    np_acts-logits-general · gemini-2.0-flash

    CD4 and CD8 T 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
    fulness
    -0.62
    RTRS
    -0.54
    cona
    -0.54
     تضيفلها
    -0.53
    cieux
    -0.52
    jahres
    -0.52
     Infórmanos
    -0.51
    ValueStyle
    -0.51
     invokingState
    -0.50
    bigcap
    -0.49
    POSITIVE LOGITS
     CDs
    0.82
     CD
    0.77
    CD
    0.70
     discs
    0.69
    💿
    0.65
     disks
    0.64
    CDK
    0.63
     cds
    0.62
     Cd
    0.60
    DVD
    0.60
    Activations Density 0.133%

    No Known Activations