© 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. 2506
    Prev
    Next
    INDEX
    Explanations

    connotative language related to communication and interpersonal dynamics

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

    direct speech or dialogue where someone tells another person 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
    SerializedSize
    -0.40
    TargetException
    -0.38
     constater
    -0.38
    BagLayout
    -0.37
     tatsäch
    -0.34
     choć
    -0.33
    nikahan
    -0.32
    RUnlock
    -0.32
     skuto
    -0.32
     qualidade
    -0.32
    POSITIVE LOGITS
     Keep
    0.55
    要不
    0.53
    Keep
    0.53
    Jangan
    0.52
    要
    0.50
    不要
    0.50
     sorry
    0.49
     uſe
    0.48
     autorytatywna
    0.48
     Unless
    0.47
    Activations Density 0.258%

    No Known Activations