© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    phrases indicating explanations or reasons

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

    periods and sentence endings that mark the completion of statements or thoughts.

    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
     noDo
    -0.88
    OGND
    -0.83
     surla
    -0.68
     мәкал
    -0.67
    AndEndTag
    -0.65
     ब्रेकडाउन
    -0.65
    protoimpl
    -0.64
    -------
    -0.62
    httphttps
    -0.62
    Rhestr
    -0.60
    POSITIVE LOGITS
    Apart
    0.71
    Moreover
    0.68
     Apart
    0.68
     Moreover
    0.66
     apart
    0.65
    Nowadays
    0.63
    Concerning
    0.61
     Nowadays
    0.59
     beside
    0.59
     besides
    0.57
    Activations Density 1.104%

    No Known Activations