© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 6026
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to dental hygiene and associated organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     browser
    -0.47
     broad
    -0.47
     Verbreitung
    -0.46
    browser
    -0.46
     breadth
    -0.46
    浏览器
    -0.44
     broadband
    -0.44
    eterangan
    -0.44
    DrawerToggle
    -0.43
     broadcast
    -0.43
    POSITIVE LOGITS
    ंदीखरीदारी
    0.58
    featureID
    0.57
    SequentialGroup
    0.53
    endcsname
    0.52
    crumb
    0.52
    AnimationsModule
    0.52
    NOPQRST
    0.51
    rungsseite
    0.49
     internetowa
    0.48
     كومونز
    0.48
    Activations Density 0.243%

    No Known Activations