© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10634
    Prev
    Next
    INDEX
    Explanations

    identifiers and terms related to software module development

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Tokens preceding identifiers (name, ID, URL, IP, id)

    np_acts-logits-general · gemini-2.0-flash

    identifiers 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
    Negative Logits
    iastical
    -0.56
     weighing
    -0.55
     IndexError
    -0.54
    weigh
    -0.49
     rated
    -0.47
     calendriers
    -0.46
    ξης
    -0.46
    elementType
    -0.46
     perfon
    -0.46
    Rated
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.71
    OrNil
    0.69
     field
    0.63
     string
    0.61
    มาะ
    0.60
     provided
    0.59
     mismatch
    0.58
    uminense
    0.57
    曖昧さ回避
    0.56
    HasForeignKey
    0.56
    Activations Density 0.481%

    No Known Activations