© 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. 37-GEMMASCOPE-RES-16K
    6. 5068
    Prev
    Next
    INDEX
    Explanations

    details related to scientific methodology and high-resolution imaging techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utilisons
    -0.36
    intéress
    -0.31
     yemek
    -0.31
    FormGroup
    -0.31
    uidado
    -0.30
    ttemberg
    -0.30
    padek
    -0.30
    DataPropertyName
    -0.30
     Kró
    -0.29
     contag
    -0.28
    POSITIVE LOGITS
     resolution
    3.69
     Resolution
    3.31
     resolutions
    3.20
    Resolution
    3.05
     resolve
    3.02
    resolution
    3.00
     resolving
    2.98
     resolved
    2.97
     RESOLUTION
    2.95
     resolves
    2.92
    Activations Density 0.783%

    No Known Activations