© 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. 11662
    Prev
    Next
    INDEX
    Explanations

    special characters and their usage in coding or markup contexts

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

    IRC chat message formatting with usernames and timestamps.

    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
    tagHelperRunner
    -0.90
     ModelExpression
    -0.89
    httphttps
    -0.82
     kasarigan
    -0.82
    +#+#
    -0.73
    IntoConstraints
    -0.71
     NSCoder
    -0.70
     fieldNum
    -0.69
    StoryboardSegue
    -0.68
    TagMode
    -0.67
    POSITIVE LOGITS
    ambién
    0.56
     élect
    0.46
    The
    0.45
    ↵↵
    0.44
    endalikan
    0.41
     telefónica
    0.41
    Summary
    0.40
    另一個
    0.40
    another
    0.40
     remet
    0.40
    Activations Density 1.148%

    No Known Activations