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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 2807
    Prev
    Next
    INDEX
    Explanations

    references to password requirements and character specifications in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.42
    նակ
    -0.36
    nesium
    -0.34
     المعيارى
    -0.33
    Cous
    -0.30
    cyklo
    -0.29
    rosia
    -0.29
    င်း
    -0.29
    =[];
    -0.29
    TintColor
    -0.29
    POSITIVE LOGITS
     character
    4.03
    character
    3.64
     Character
    3.59
    Character
    3.41
     characters
    3.31
     CHARACTER
    3.27
     karakter
    3.14
     Characters
    2.98
     Charakter
    2.95
    characters
    2.92
    Activations Density 0.922%

    No Known Activations