© 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. 15481
    Prev
    Next
    INDEX
    Explanations

    connections between entities and their functions or roles

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

    phrases expressing personal knowledge or understanding about someone or something.

    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
    itario
    -0.38
     TextInputType
    -0.38
    RegistryLite
    -0.35
     Rukh
    -0.35
    coledì
    -0.35
    __(/*!
    -0.35
     Universidades
    -0.35
     Ombudsman
    -0.35
    Дорогие
    -0.34
    labus
    -0.34
    POSITIVE LOGITS
     better
    2.09
    better
    1.80
     mejor
    1.75
     mieux
    1.67
     meglio
    1.63
     melhor
    1.61
     лучше
    1.55
    Better
    1.53
     bättre
    1.45
     BETTER
    1.45
    Activations Density 0.633%

    No Known Activations