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. 3-GEMMASCOPE-RES-16K
    6. 16191
    Prev
    Next
    INDEX
    Explanations

    the word "example" and its various repetitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.67
    łoż
    -0.49
     Saran
    -0.48
    SCT
    -0.47
    Werk
    -0.47
    Scrap
    -0.46
     ResultSet
    -0.45
     Wabash
    -0.45
    SUPPLEMENT
    -0.44
     zin
    -0.44
    POSITIVE LOGITS
    example
    2.65
     example
    1.61
    Example
    1.45
     Example
    1.36
    exemple
    1.29
    EXAMPLE
    1.25
     EXAMPLE
    1.25
     ejemplo
    1.17
    examples
    1.16
     exemplo
    1.11
    Activations Density 0.037%

    No Known Activations