© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 16301
    Prev
    Next
    INDEX
    Explanations

    words related to containers, especially for liquids or substances

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

    containers like bowls, buckets, or baskets that can hold things.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "bucket" and phrases containing "bucket" with adjacent words like "list," "of," and "fuls."

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    AddTagHelper
    -0.42
     OnInit
    -0.41
     courseId
    -0.39
     getProperty
    -0.38
    featureID
    -0.38
     postId
    -0.37
     createdBy
    -0.37
    VersionUID
    -0.36
     newName
    -0.36
     Notre
    -0.35
    POSITIVE LOGITS
    fuls
    0.83
    ful
    0.81
     containing
    0.59
     lleno
    0.59
     Deckel
    0.57
     filled
    0.57
     '\\;'
    0.56
     lid
    0.54
     FILLER
    0.54
    CppMethod
    0.53
    Activations Density 0.432%

    No Known Activations