© 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. 39-GEMMASCOPE-RES-16K
    11. 1202
    Prev
    Next
    INDEX
    Explanations

    questions and concerns about personal well-being and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.47
     '\\;'
    -0.43
    aarrggbb
    -0.41
    ########.
    -0.40
    
    -0.40
    يميديا
    -0.40
    autorest
    -0.38
    haikusbot
    -0.38
    kheim
    -0.37
     }}"></
    -0.33
    POSITIVE LOGITS
     adding
    3.20
     add
    3.11
     Adding
    3.02
     added
    2.91
     adds
    2.88
    Adding
    2.84
     Add
    2.81
    adding
    2.72
    Add
    2.66
    add
    2.61
    Activations Density 2.882%

    No Known Activations