© 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. 8228
    Prev
    Next
    INDEX
    Explanations

    references to components of a system or structure

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

    numbers three, four, or five

    np_acts-logits-general · gemini-2.0-flash

    numbers and counts

    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
    Thirty
    -0.71
    Sixty
    -0.63
    Twenty
    -0.62
    Fifteen
    -0.62
     Thirty
    -0.62
    thirty
    -0.60
     ribuan
    -0.60
    Forty
    -0.59
    ninth
    -0.59
     thirteenth
    -0.59
    POSITIVE LOGITS
     т
    0.86
     세
    0.76
     thr
    0.74
     triplet
    0.68
     three
    0.67
     tri
    0.62
     네
    0.62
     τ
    0.62
    三
    0.60
    viert
    0.60
    Activations Density 0.371%

    No Known Activations