© 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. 12420
    Prev
    Next
    INDEX
    Explanations

    phrases referencing specific times, dates, or sequences

    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
     nakalista
    -0.50
    .*")]
    -0.46
    bitField
    -0.43
    -------
    -0.39
     &___
    -0.39
    \{\\
    -0.38
    المشاركات
    -0.34
    runApp
    -0.33
    unitas
    -0.31
     gi
    -0.31
    POSITIVE LOGITS
     steder
    0.80
     way
    0.60
     للمعارف
    0.58
     gånger
    0.56
    ături
    0.56
    เดียว
    0.54
    handedly
    0.53
    seguida
    0.52
    matically
    0.52
     mattina
    0.51
    Activations Density 0.565%

    No Known Activations