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. 19-GEMMASCOPE-RES-16K
    6. 3930
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to population statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.57
     Bell
    -0.54
    thical
    -0.53
    swire
    -0.51
    thang
    -0.49
    sigen
    -0.48
    vend
    -0.47
    mines
    -0.47
    Bell
    -0.47
    kang
    -0.46
    POSITIVE LOGITS
     millions
    2.06
     Millions
    1.79
    millions
    1.72
    Millions
    1.66
     million
    1.60
     milioni
    1.51
     millones
    1.48
     milhões
    1.43
     millón
    1.42
     Millionen
    1.33
    Activations Density 0.252%

    No Known Activations