© 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. 38-GEMMASCOPE-RES-16K
    6. 10299
    Prev
    Next
    INDEX
    Explanations

    code structures and programming logic, particularly involving limits and interface checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    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
    -0.59
    -------------</
    -0.58
    ſchaft
    -0.58
    __':
    
    -0.56
    militar
    -0.56
    ----</
    -0.56
    "]();
    -0.54
    smo
    -0.54
    niſſe
    -0.54
    iſten
    -0.53
    POSITIVE LOGITS
     tampoco
    0.46
     Asamblea
    0.43
     insectos
    0.43
     asamblea
    0.41
     rocas
    0.41
     varones
    0.40
     bahía
    0.40
     liberdade
    0.39
     localidad
    0.39
     myö
    0.38
    Activations Density 1.921%

    No Known Activations