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. 11-GEMMASCOPE-RES-16K
    6. 7244
    Prev
    Next
    INDEX
    Explanations

    references to Michael Jackson and his legacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AppSettings
    -0.80
    :\/\/
    -0.79
    ing
    -0.74
     Sext
    -0.69
     neri
    -0.69
    citas
    -0.69
     Clio
    -0.68
    oom
    -0.68
    </em>
    -0.67
     roo
    -0.66
    POSITIVE LOGITS
     Michael
    1.16
     Michaels
    1.13
    Micha
    1.08
    Michael
    0.97
    çalves
    0.94
    MICHAEL
    0.93
     Micha
    0.93
     Ryanair
    0.92
     MICHAEL
    0.90
     Mike
    0.86
    Activations Density 0.230%

    No Known Activations