© 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. 39-GEMMASCOPE-RES-16K
    6. 4487
    Prev
    Next
    INDEX
    Explanations

    structures and elements related to data analysis, particularly in scientific contexts

    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
    twimg
    -0.65
     '\\;'
    -0.63
    CppCodeGen
    -0.59
    Datuak
    -0.59
    ,»
    -0.58
    QMetaType
    -0.55
    
    -0.53
    
    -0.52
     utafitiHapana
    -0.52
    endpush
    -0.52
    POSITIVE LOGITS
    ________________
    1.89
    ................
    1.86
    ----------------
    1.78
    ****************
    1.74
    ================
    1.50
    …………………………………………
    1.48
    ################
    1.47
    ______________
    1.47
    ////////////////
    1.46
    ………………………………
    1.45
    Activations Density 1.623%

    No Known Activations