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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16234
    Prev
    Next
    INDEX
    Explanations

    functional programming concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.54
    évaluateur
    -0.53
    RenderAtEndOf
    -0.51
     AssemblyProduct
    -0.50
    verwijspagina
    -0.48
    angliski
    -0.47
     للاسماء
    -0.47
    webElementGuid
    -0.47
    ViewImports
    -0.46
     متعلقه
    -0.46
    POSITIVE LOGITS
     following
    2.41
    following
    2.08
     folgende
    1.97
    以下
    1.88
     följande
    1.86
     Following
    1.83
     følgende
    1.81
    Following
    1.80
     seguinte
    1.79
     folgenden
    1.78
    Activations Density 1.592%

    No Known Activations