Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9191
    Prev
    Next
    INDEX
    Explanations

    concepts related to professional etiquette and business interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.56
    setVerticalGroup
    -0.47
    だが
    -0.46
    だったが
    -0.46
    AddHtmlAttribute
    -0.46
    providedIn
    -0.45
     {}));
    -0.45
    protoimpl
    -0.45
    であるが
    -0.44
     poveznice
    -0.44
    POSITIVE LOGITS
     yourself
    0.96
     itſelf
    0.90
     purpoſe
    0.87
     your
    0.87
     Anſ
    0.86
     myſelf
    0.86
    your
    0.81
     pleaſure
    0.80
     houſe
    0.80
     faſt
    0.77
    Activations Density 0.358%

    No Known Activations