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. 15-GEMMASCOPE-RES-16K
    6. 8707
    Prev
    Next
    INDEX
    Explanations

    references to Michael Jackson

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.82
     Audiodateien
    -0.82
     cdti
    -0.80
    </caption>
    -0.77
    AppSettings
    -0.74
    .")]
    -0.74
     scania
    -0.69
    */}
    -0.69
     seta
    -0.69
    ).</
    -0.69
    POSITIVE LOGITS
     Michael
    1.00
     Michaels
    0.96
    Micha
    0.93
     Mike
    0.92
    Michael
    0.84
    MICHAEL
    0.76
     MICHAEL
    0.74
    angelo
    0.73
    Mike
    0.72
     MIKE
    0.70
    Activations Density 0.069%

    No Known Activations