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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9433
    Prev
    Next
    INDEX
    Explanations

    references to historical events and states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.99
    addPreferredGap
    -0.89
    bootstrapcdn
    -0.89
    setVerticalGroup
    -0.81
    endphp
    -0.81
    WithIOException
    -0.79
     wikipagina
    -0.79
    invokeLater
    -0.77
     Wikiseite
    -0.76
    
    -0.75
    POSITIVE LOGITS
     previously
    0.87
     раньше
    0.83
     Previously
    0.82
     früher
    0.81
     formerly
    0.81
     ago
    0.80
    เคย
    0.79
    Previously
    0.79
    previously
    0.78
     Formerly
    0.78
    Activations Density 0.245%

    No Known Activations