© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 13506
    Prev
    Next
    INDEX
    Explanations

    key terms and concepts related to systematic methods and processes in scientific research and writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.43
    RegistryLite
    -0.36
    __':
    -0.34
    깝
    -0.34
     دچار
    -0.32
     مُعرِّف
    -0.32
    {}/
    -0.32
    ngOn
    -0.31
     Varies
    -0.31
    ⓘ
    -0.31
    POSITIVE LOGITS
     creation
    1.67
     removal
    1.45
     introduction
    1.45
     formation
    1.30
     elimination
    1.29
     establishment
    1.29
     completion
    1.28
     issuance
    1.27
     emergence
    1.25
     imposition
    1.25
    Activations Density 2.748%

    No Known Activations