© 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. 663
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structures

    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
     tartalomajánló
    -0.48
    "]();
    -0.47
    SequentialGroup
    -0.46
    Personendaten
    -0.45
     ""],
    -0.44
    CopyWith
    -0.44
    militar
    -0.43
    んの
    -0.42
    disse
    -0.42
    GEBURTS
    -0.42
    POSITIVE LOGITS
    ähteet
    0.52
     tampoco
    0.51
     ocasiones
    0.47
     anhänger
    0.46
    afficheront
    0.45
     Tatsache
    0.44
     myö
    0.44
     bahía
    0.44
     lisäksi
    0.44
    Conclusiones
    0.43
    Activations Density 2.618%

    No Known Activations