© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 11455
    Prev
    Next
    INDEX
    Explanations

    content related to organizational meetings and environmental studies

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

    formal official documents and procedural announcements.

    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
     colour
    -0.59
     colours
    -0.57
     centre
    -0.57
     behaviour
    -0.56
     favourite
    -0.55
     rumours
    -0.55
     coloured
    -0.55
     defence
    -0.54
     organisers
    -0.54
     neighbours
    -0.53
    POSITIVE LOGITS
     statewide
    0.83
     Statewide
    0.80
     jurisdictional
    0.80
     utilizing
    0.72
     prioritized
    0.71
     federally
    0.70
     permittee
    0.70
     pursuant
    0.70
    ktır
    0.67
     hydrologic
    0.67
    Activations Density 0.712%

    No Known Activations