© 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. 24-GEMMASCOPE-RES-16K
    11. 13711
    Prev
    Next
    INDEX
    Explanations

    proper nouns referring to people or entities involved in legal contexts

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

    ending in "on," "in," or "yl"

    np_acts-logits-general · gemini-2.0-flash

    names and relating words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.91
     AssemblyCulture
    -0.64
    出版年
    -0.60
    ParallelGroup
    -0.57
    `.`
    -0.54
    IActionResult
    -0.54
     punya
    -0.51
    webElementGuid
    -0.48
     deaths
    -0.48
     لدي
    -0.48
    POSITIVE LOGITS
     who
    1.02
     whom
    0.84
     during
    0.76
     riguardo
    0.76
     after
    0.75
    whom
    0.71
     quien
    0.68
    who
    0.66
     prior
    0.65
     regarding
    0.64
    Activations Density 0.499%

    No Known Activations