© 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. 10806
    Prev
    Next
    INDEX
    Explanations

    numeric values and associated punctuation related to measurements or statistics

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

    Appears before possessive "s"

    np_acts-logits-general · gemini-2.0-flash

    2/0

    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
     Utilizing
    -0.82
    — 
    -0.78
    ोड़
    -0.78
     mold
    -0.77
     color
    -0.75
    httphttps
    -0.74
    beled
    -0.74
    Honors
    -0.73
     Savior
    -0.73
     Honorable
    -0.72
    POSITIVE LOGITS
     şi
    0.67
     programme
    0.66
     stabilisation
    0.63
    ●
    0.62
     ţ
    0.61
     defence
    0.61
     civilised
    0.61
     specialises
    0.60
     favourite
    0.60
     organisational
    0.59
    Activations Density 0.077%

    No Known Activations