© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3953
    Prev
    Next
    INDEX
    Explanations

    phrases indicating proportions and quantities related to measurements or assessments

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

    Followed by quantity/degree adjectives

    np_acts-logits-general · gemini-2.0-flash

    degree or extent

    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
     OFDb
    -0.79
    AndEndTag
    -0.79
    RegistryLite
    -0.74
    EndContext
    -0.74
     صوتيه
    -0.73
    afficheront
    -0.73
    ValueStyle
    -0.71
     MainAxisSize
    -0.70
    tagHelperRunner
    -0.70
     @"/
    -0.69
    POSITIVE LOGITS
     appreciable
    1.13
     significant
    1.10
     considerable
    1.00
     substantial
    1.00
     fair
    0.96
     sufficient
    0.94
     reasonable
    0.91
    fair
    0.89
     sizeable
    0.88
     sizable
    0.88
    Activations Density 0.369%

    No Known Activations