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. 4-GEMMASCOPE-RES-16K
    6. 3138
    Prev
    Next
    INDEX
    Explanations

    first-person singular pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -0.68
     Theſe
    -0.66
     whoſe
    -0.64
     Eſ
    -0.62
     Diſ
    -0.61
     Azo
    -0.60
     Ferdin
    -0.59
     noastre
    -0.56
     diſt
    -0.56
     monasterio
    -0.55
    POSITIVE LOGITS
     I
    0.95
    tvguidetime
    0.85
    LEncoder
    0.83
     []:
    0.81
    __*/
    0.81
    MemoryWarning
    0.79
     وتسجيلات
    0.77
    Datuak
    0.76
    NamedQueries
    0.74
    RenderAtEndOf
    0.73
    Activations Density 0.166%

    No Known Activations