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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 2115
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or topics related to legal cases and areas of expertise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.55
    ähän
    -0.51
     spéciale
    -0.50
     enää
    -0.48
    resave
    -0.48
    fois
    -0.47
     vroeger
    -0.47
    urably
    -0.46
     spéciaux
    -0.46
     autrefois
    -0.46
    POSITIVE LOGITS
    ana
    1.22
    na
    1.19
    enumi
    1.11
    ina
    1.05
    ANA
    1.00
    NA
    0.93
    ena
    0.87
    INA
    0.86
    ना
    0.84
    ナ
    0.77
    Activations Density 2.000%

    No Known Activations