© 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. 36-GEMMASCOPE-RES-16K
    6. 16205
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their attributes within programming or configuration contexts

    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
     Nop
    -0.35
    Pyx
    -0.34
    ·
    -0.34
    await
    -0.33
     unidad
    -0.32
     Upon
    -0.32
    Cooler
    -0.31
    ']>
    -0.30
     Agr
    -0.30
     convenient
    -0.30
    POSITIVE LOGITS
     =>
    1.51
    =>
    1.02
    "=>
    0.82
     =>
    
    0.79
    =>$
    0.78
     ⇒
    0.78
     ==>
    0.77
    Rightarrow
    0.75
    ]=>
    0.75
    '=>
    0.72
    Activations Density 0.182%

    No Known Activations