© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8947
    Prev
    Next
    INDEX
    Explanations

    expressions of distress and pleas for help

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

    Instances of the word "please" appearing in dialogue or emphatic requests.

    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
    AddHtmlAttribute
    -0.56
     surla
    -0.54
     MainAxisSize
    -0.51
    IndentedString
    -0.51
     wohl
    -0.50
     dezelve
    -0.50
    Autoritní
    -0.47
    inheritdoc
    -0.46
    Yup
    -0.45
    fortunate
    -0.44
    POSITIVE LOGITS
     please
    1.41
     PLEASE
    1.29
    please
    1.23
     Please
    1.15
    Please
    1.13
    PLEASE
    1.13
     plz
    1.02
     Bitte
    0.98
     pls
    0.94
     пожалуйста
    0.92
    Activations Density 0.189%

    No Known Activations