© 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. 3502
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and chemical compounds

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

    Tokens enclosed in parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    negative or positive

    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
     Decreased
    -0.78
     decreasing
    -0.78
    Minus
    -0.77
     Decrease
    -0.76
     decreases
    -0.75
    decrease
    -0.75
     decreased
    -0.75
     descending
    -0.74
     lowering
    -0.74
    Decrease
    -0.74
    POSITIVE LOGITS
    ,+
    0.89
    =+
    0.87
     positive
    0.84
    glEnable
    0.81
     positives
    0.76
    WebVitals
    0.75
    出版年
    0.74
    ^{+
    0.74
     Positive
    0.74
     positively
    0.73
    Activations Density 0.728%

    No Known Activations