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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14419
    Prev
    Next
    INDEX
    Explanations

    elements related to actions and processes, especially in a legal or evaluative context

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

    adjectives describing qualities or characteristics, particularly those with high activation values on words like "subjective," "objective," "creative," "important," "independent," "distasteful," "bodily," and "foreign."

    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
    newBuilder
    -0.33
     brind
    -0.32
     cursed
    -0.31
    Status
    -0.31
    蒴
    -0.30
    entibus
    -0.30
    模
    -0.30
     createTime
    -0.29
     szczę
    -0.29
    getCustomer
    -0.29
    POSITIVE LOGITS
     aspect
    2.36
     aspects
    2.25
     component
    2.05
     element
    2.03
    aspects
    1.93
     elements
    1.88
    aspect
    1.85
     Aspects
    1.81
     Aspect
    1.71
     aspek
    1.68
    Activations Density 0.859%

    No Known Activations