© 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. 6717
    Prev
    Next
    INDEX
    Explanations

    references to specific targets or properties in a framework

    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
     rowCount
    -0.48
    škai
    -0.47
     createdBy
    -0.45
     nicio
    -0.45
     Nw
    -0.45
     demikian
    -0.44
    Geplaatst
    -0.44
    isler
    -0.44
     Vann
    -0.43
     pernikahan
    -0.42
    POSITIVE LOGITS
     target
    1.91
     Target
    1.83
    target
    1.83
    Target
    1.77
     TARGET
    1.65
    TARGET
    1.53
     targets
    1.46
     getTarget
    1.45
    getTarget
    1.45
     Targets
    1.43
    Activations Density 0.108%

    No Known Activations