© 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. 18-GEMMASCOPE-RES-16K
    11. 15716
    Prev
    Next
    INDEX
    Explanations

    references to case studies or reports

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

    "Case" followed by a preposition or noun

    np_acts-logits-general · gemini-2.0-flash

    case report, study, or presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     صوتيه
    -0.84
     Theſe
    -0.84
    yntaxException
    -0.80
     Mercurio
    -0.80
     Monfieur
    -0.78
     diſt
    -0.76
    ArrowToggle
    -0.75
     Administrativna
    -0.73
     سكانية
    -0.73
     للمعارف
    -0.73
    POSITIVE LOGITS
     Cases
    1.00
    Cases
    1.00
    cases
    0.98
     CASE
    0.98
     cases
    0.97
     Case
    0.92
    CASE
    0.90
     study
    0.90
     CASES
    0.86
    case
    0.85
    Activations Density 0.148%

    No Known Activations