© 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. 11012
    Prev
    Next
    INDEX
    Explanations

    references to formal academic structures or processes

    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
    oa̍t
    -0.43
    __":
    -0.42
    featureID
    -0.41
    __':
    -0.40
    >");
    -0.40
    AccessFile
    -0.40
    onViewCreated
    -0.38
    gogo
    -0.37
    السكان
    -0.35
     gouver
    -0.35
    POSITIVE LOGITS
     eventual
    0.59
     occasional
    0.55
     short
    0.53
     brief
    0.53
     double
    0.52
     yapılan
    0.51
     frequent
    0.50
     periodic
    0.50
     による
    0.49
    による
    0.48
    Activations Density 1.077%

    No Known Activations