© 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. 4483
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to best practices and recommendations in programming or technology

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

    comparative statements using "it would be" constructions.

    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
    enterOuterAlt
    -0.68
    Portály
    -0.45
    OuterAlt
    -0.44
    पया
    -0.43
    ArrowToggle
    -0.43
    portál
    -0.43
     دیکھیے
    -0.40
    лтемелер
    -0.40
    TagNumber
    -0.37
     مفص
    -0.37
    POSITIVE LOGITS
     best
    2.39
     better
    2.28
     mejor
    2.20
    better
    2.11
     melhor
    2.11
    best
    2.05
     лучше
    2.03
    Better
    1.95
     meglio
    1.95
     Better
    1.85
    Activations Density 0.719%

    No Known Activations