Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 2398
    Prev
    Next
    INDEX
    Explanations

    references to the Catholic Church and its associated institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (;;)
    -0.74
    RenderAtEndOf
    -0.73
     AssemblyVersion
    -0.72
     numberOfRows
    -0.64
    Refunds
    -0.63
     tartalomajánló
    -0.63
    WRP
    -0.62
     compactness
    -0.61
     Racine
    -0.61
    ligible
    -0.60
    POSITIVE LOGITS
    yntaxException
    0.55
     Sociales
    0.53
     catholic
    0.51
    WriteBarrier
    0.51
    corrhi
    0.51
    addPreferredGap
    0.51
     bishops
    0.51
     Sigism
    0.50
    pulumi
    0.49
     Daylight
    0.49
    Activations Density 0.807%

    No Known Activations