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. 3-GEMMASCOPE-RES-16K
    6. 10020
    Prev
    Next
    INDEX
    Explanations

    mentions of "Tal" and its derivatives, which likely relate to a specific subject or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allen
    -0.59
     luce
    -0.51
     Wheeler
    -0.51
     versch
    -0.50
     تک
    -0.49
    JG
    -0.48
    ǧ
    -0.48
     forme
    -0.48
    uker
    -0.47
    weakSelf
    -0.47
    POSITIVE LOGITS
     Tal
    2.60
    Tal
    2.56
     tal
    2.54
    tal
    2.20
     TAL
    1.92
    TAL
    1.88
     Talbot
    1.61
     Tally
    1.46
     Tali
    1.40
    tals
    1.37
    Activations Density 0.145%

    No Known Activations