© 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. 35-GEMMASCOPE-RES-16K
    11. 12255
    Prev
    Next
    INDEX
    Explanations

    opening and closing curly braces "{" and "}"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.43
    brainly
    -0.42
    EndGlobalSection
    -0.36
     الوطنيه
    -0.35
    homonymie
    -0.34
     fin
    -0.33
     للمعارف
    -0.33
     håll
    -0.33
    Cordialement
    -0.33
    Stu
    -0.33
    POSITIVE LOGITS
     '\\;'
    0.60
    BeginContext
    0.52
    .*")]
    0.50
    Werdegang
    0.47
     برانيه
    0.47
     تكبرها
    0.47
    IsContent
    0.46
    MemoryWarning
    0.46
     dAtA
    0.45
     فريبيس
    0.45
    Activations Density 0.651%

    No Known Activations