© 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. 12569
    Prev
    Next
    INDEX
    Explanations

    technical terms related to neurobiology and their effects on health conditions

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

    Capitalized words or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    academic institutions and addresses

    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
     varandra
    -0.84
     

    -0.79
     ―
    -0.79
     ușor
    -0.78
     démocr
    -0.77
     bēr
    -0.77
     (\
    -0.76
     silenzio
    -0.74
     gând
    -0.74
     
    -0.73
    POSITIVE LOGITS
    ’?
    0.77
    “:
    0.73
    “.
    0.72
    :.
    0.68
    ”?
    0.66
    .'”
    0.65
    ”…
    0.65
    AddHtmlAttribute
    0.64
     :}
    0.62
    :”
    0.62
    Activations Density 0.029%

    No Known Activations