© 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. 16033
    Prev
    Next
    INDEX
    Explanations

    assertions and advice regarding personal determination and success

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

    punctuation marks, particularly commas and periods at the end of sentences or clauses.

    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
    bootstrapcdn
    -0.71
    twimg
    -0.63
    haikusbot
    -0.59
    DockStyle
    -0.59
     $_"
    -0.55
    ChildScrollView
    -0.54
     getchar
    -0.52
     تضيفلها
    -0.52
    Zeneca
    -0.52
    ußt
    -0.51
    POSITIVE LOGITS
     “
    2.28
     "
    2.20
     “[
    1.84
     “…
    1.82
     „
    1.80
     "...
    1.78
     "[
    1.71
    「
    1.70
     “...
    1.70
     «
    1.66
    Activations Density 4.197%

    No Known Activations