© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 12467
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical methods and descriptors

    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
    orszá
    -0.57
     ThemeData
    -0.52
     Irán
    -0.52
    føring
    -0.50
    AlreadyExists
    -0.50
    BorderColor
    -0.50
     Teléfono
    -0.49
    WriteLiteral
    -0.49
    Cliquez
    -0.48
    Gemeinden
    -0.48
    POSITIVE LOGITS
    tive
    0.89
    sive
    0.82
    ative
    0.82
    itive
    0.82
    ctive
    0.79
    lective
    0.75
    ective
    0.73
    estive
    0.71
    rative
    0.70
    ulative
    0.70
    Activations Density 0.348%

    No Known Activations