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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2619
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and diagnostics

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

    Comes after symbols or special characters

    np_acts-logits-general · gemini-2.0-flash

    d followed by y, n, or w

    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
     démocratique
    -0.81
     deuter
    -0.78
     Denmark
    -0.76
     Doppler
    -0.75
     DP
    -0.74
     dp
    -0.74
    DP
    -0.73
     Dirichlet
    -0.73
    democratic
    -0.73
     dandelion
    -0.72
    POSITIVE LOGITS
    styleable
    0.38
    InjectMocks
    0.37
    ArrowToggle
    0.36
    Ссылки
    0.35
    specialchars
    0.35
     (!__
    0.35
    StructEnd
    0.35
    expandindo
    0.34
    zelle
    0.34
    zegorz
    0.34
    Activations Density 0.833%

    No Known Activations