© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7012
    Prev
    Next
    INDEX
    Explanations

    variations and types of "forms" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    printStackTrace
    -0.60
     sánchez
    -0.60
    expandindo
    -0.59
     McAllister
    -0.56
    pixel
    -0.56
    centralwidget
    -0.56
    AddField
    -0.55
     myel
    -0.55
     onely
    -0.54
    penny
    -0.53
    POSITIVE LOGITS
     form
    1.57
     Form
    1.53
     FORM
    1.41
    form
    1.36
    Form
    1.36
     Forms
    1.21
     forms
    1.21
    FORM
    1.10
    Forms
    1.05
    forms
    1.05
    Activations Density 0.162%

    No Known Activations