© 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. 21-GEMMASCOPE-RES-16K
    6. 16303
    Prev
    Next
    INDEX
    Explanations

    references to locations and nationalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.72
    الدراسه
    -0.56
    IntoConstraints
    -0.54
    万美元
    -0.52
    cagon
    -0.50
    cahontas
    -0.50
     comuniques
    -0.50
    nasium
    -0.49
    luia
    -0.49
     Rasmus
    -0.49
    POSITIVE LOGITS
    Спољашње
    0.40
     twier
    0.39
     noqa
    0.39
     cultuur
    0.38
     German
    0.36
     culturali
    0.36
     cultural
    0.36
    spd
    0.35
     δημο
    0.35
     herab
    0.34
    Activations Density 1.196%

    No Known Activations