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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 4827
    Prev
    Next
    INDEX
    Explanations

    Japanese phrases related to sin and repentance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Non-English language fragments

    np_acts-logits-general · gemini-2.0-flash

    multilingual mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     houſe
    -0.89
     Jefus
    -0.89
     Majefty
    -0.79
     purpoſe
    -0.79
     Monfieur
    -0.76
     myſelf
    -0.76
     juſ
    -0.73
     himſelf
    -0.72
     Eſ
    -0.72
     ſche
    -0.72
    POSITIVE LOGITS
     (…)
    0.59
    !...
    0.58
    randrange
    0.56
     anteriore
    0.54
     semblables
    0.54
     brinquedos
    0.53
     [...
    0.53
     orgánico
    0.52
     cardiaque
    0.50
     (...)
    0.50
    Activations Density 0.064%

    No Known Activations