© 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. 14779
    Prev
    Next
    INDEX
    Explanations

    the presence of the prefix "pro" indicating a professional or positive aspect

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

    "pro" followed by a word ending in "ent" or "and"

    np_acts-logits-general · gemini-2.0-flash

    proband, proffers, proviral, proapoptotic

    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
    MigrationBuilder
    -0.80
    Välislingid
    -0.67
     betweenstory
    -0.67
     CreateTagHelper
    -0.66
    ngdoc
    -0.61
     <>",
    -0.61
    penters
    -0.60
     otomatig
    -0.60
    ftagPool
    -0.60
    saraba
    -0.59
    POSITIVE LOGITS
    ruptedException
    0.49
    ComponentScan
    0.43
     PAGES
    0.42
    ])));
    0.41
     Domini
    0.41
    entrion
    0.40
     domin
    0.40
     Scotts
    0.40
     setInterval
    0.40
     Bols
    0.40
    Activations Density 0.230%

    No Known Activations