© 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. 1359
    Prev
    Next
    INDEX
    Explanations

    phrases related to mistakes, accountability, and the consequences of actions

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

    contractions with apostrophes, particularly those indicating negation or possession in longer passages.

    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
     forbed
    -0.37
     yolu
    -0.37
     cordes
    -0.34
     tilgjenge
    -0.33
     estrictamente
    -0.32
    clusal
    -0.32
     sikkert
    -0.32
     znal
    -0.32
     gruesa
    -0.32
     활
    -0.32
    POSITIVE LOGITS
     للاسماء
    0.71
    oa̍t
    0.70
     scandals
    0.70
    expandindo
    0.69
    featureID
    0.68
     infamous
    0.68
    MemoryWarning
    0.68
     Afghanistan
    0.67
    principalColumn
    0.67
     يتيمه
    0.66
    Activations Density 1.127%

    No Known Activations