© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4961
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and evaluations

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

    Following tokens like "site", "stand", "subject", or "sample"

    np_acts-logits-general · gemini-2.0-flash

    specific characteristics and measurements

    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
     définiti
    -0.72
     springfox
    -0.64
     prochaines
    -0.59
     élevés
    -0.58
     supérieurs
    -0.58
     réguli
    -0.58
     élevées
    -0.57
     remarqué
    -0.57
     donnés
    -0.56
     esprits
    -0.56
    POSITIVE LOGITS
     size
    0.79
     sizes
    0.79
    specific
    0.78
     characteristics
    0.74
     selection
    0.73
     specific
    0.70
     types
    0.69
     specifics
    0.69
    -
    0.69
     performance
    0.67
    Activations Density 1.237%

    No Known Activations