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. 13-GEMMASCOPE-RES-16K
    6. 7102
    Prev
    Next
    INDEX
    Explanations

    interrogative words and phrases that indicate questions or inquiries

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

    Romance-language (French/Spanish/Portuguese) clause-introducing words—especially interrogative/relative conjunctions and pronouns that begin subordinate or question clauses.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.11
     Diſ
    -0.97
     iſt
    -0.97
     Majefty
    -0.96
     purpoſe
    -0.96
     Chriſt
    -0.96
     myſelf
    -0.94
     Jefus
    -0.94
     eſt
    -0.94
    ſelf
    -0.93
    POSITIVE LOGITS
     Que
    1.09
     que
    1.06
    Que
    1.06
     QUE
    0.91
    RenderAtEndOf
    0.83
     że
    0.79
     Qui
    0.78
    que
    0.78
    Qui
    0.77
     hogy
    0.71
    Activations Density 0.040%

    No Known Activations