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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 13943
    Prev
    Next
    INDEX
    Explanations

    code segments related to notifications and user alerts

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

    displaying messages or alerts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.64
    IntoConstraints
    -0.54
     CreateTagHelper
    -0.52
    ᅠ
    -0.45
    Curious
    -0.44
    thâu
    -0.43
    ModelSerializer
    -0.43
    Халык
    -0.43
     jadx
    -0.43
     Roskov
    -0.43
    POSITIVE LOGITS
    astify
    0.81
    AnimationsModule
    0.55
    sweetalert
    0.52
    MessageState
    0.46
    makeText
    0.46
    basicConfig
    0.43
     MessageBoxIcon
    0.43
    aarrggbb
    0.42
    ismet
    0.41
    arakhand
    0.39
    Activations Density 0.013%

    No Known Activations