© 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. 38-GEMMASCOPE-RES-16K
    11. 12914
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intent or obligation related to future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.69
    httphttps
    -0.60
     kasarigan
    -0.55
    consulté
    -0.54
    InputBorder
    -0.50
    AutoScaleMode
    -0.48
    VersionUID
    -0.47
    曖昧さ回避
    -0.46
     <<<<<<<<<<<<<<
    -0.46
    rungsseite
    -0.45
    POSITIVE LOGITS
     notice
    0.82
     regret
    0.77
     notices
    0.66
     want
    0.65
     regrets
    0.65
     noticing
    0.64
     regretted
    0.63
     hear
    0.63
     noticed
    0.62
    notice
    0.62
    Activations Density 0.214%

    No Known Activations