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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12065
    Prev
    Next
    INDEX
    Explanations

    specific organizational, geographic, and legislative references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mayores
    -0.33
    PopupWindow
    -0.33
     коп
    -0.33
    DataReader
    -0.33
     Tuc
    -0.32
    ffilm
    -0.32
     Trujillo
    -0.31
    ApiModel
    -0.31
    UseVisualStyle
    -0.31
     Seelen
    -0.31
    POSITIVE LOGITS
    gdx
    0.84
     Houston
    0.75
    Houston
    0.73
     Texan
    0.73
     Gujarat
    0.73
     Texans
    0.73
     Astros
    0.71
     Gujarati
    0.71
     TEXAS
    0.70
    iſchen
    0.68
    Activations Density 1.052%

    No Known Activations