© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 8665
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes in web content

    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
     Administrativna
    -0.66
     Bre
    -0.49
     MenuItem
    -0.46
     Recipient
    -0.46
     BRE
    -0.45
     Knudsen
    -0.45
     referencing
    -0.45
     resmi
    -0.45
    ródło
    -0.43
    ichtig
    -0.43
    POSITIVE LOGITS
    addGroup
    3.56
    SourceChecksum
    0.82
    TagMode
    0.71
    AutoField
    0.67
    AutoScaleMode
    0.65
    RefNanny
    0.61
    disposing
    0.60
    principalColumn
    0.60
    tagHelperRunner
    0.60
     protoimpl
    0.60
    Activations Density 0.065%

    No Known Activations