© 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. 14190
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and mathematical expressions

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

    Mathematical equations/expressions

    np_acts-logits-general · gemini-2.0-flash

    prime factors of 1 and 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
     autorytatywna
    -0.87
     noDo
    -0.84
    '][]
    -0.84
    Sucesor
    -0.75
    webElementXpaths
    -0.70
    encodeWith
    -0.70
    invokeLater
    -0.69
    *)&
    -0.69
    hoeddwyd
    -0.67
    Tikang
    -0.66
    POSITIVE LOGITS
    st
    1.23
    1
    1.15
    0
    1.11
    2
    1.05
    5
    0.95
    6
    0.91
    3
    0.88
    4
    0.88
    8
    0.87
    9
    0.84
    Activations Density 1.680%

    No Known Activations