Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 14882
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physics, particularly those involving spins and states of matter

    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
    Autoritní
    -0.64
    OGND
    -0.62
     ویکی‌پدیای
    -0.54
     AssemblyTitle
    -0.53
    ロウィン
    -0.52
     autorytatywna
    -0.51
     AssemblyVersion
    -0.50
     Obrador
    -0.50
    SharedDtor
    -0.49
    majánló
    -0.49
    POSITIVE LOGITS
     الرياضيه
    0.38
    migrationBuilder
    0.36
     disambiguazione
    0.36
    تقاوى
    0.35
    DropColumn
    0.35
     счет
    0.34
    Derbyniad
    0.34
     himſelf
    0.34
    SWIG
    0.33
    NECTION
    0.32
    Activations Density 2.349%

    No Known Activations