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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13958
    Prev
    Next
    INDEX
    Explanations

    components and elements related to user interface design in programming

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

    GUI element or start of turn marker

    np_acts-logits-general · gemini-2.0-flash

    UI elements like TextView and JLabel

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RTEE
    -0.50
    AddTagHelper
    -0.47
    각주
    -0.47
    StandardCharsets
    -0.46
    Παραπομπές
    -0.45
     שוליים
    -0.45
    来歴
    -0.42
     NSCoder
    -0.42
    VersionUID
    -0.42
    Välislingid
    -0.41
    POSITIVE LOGITS
     QLabel
    0.74
    TextView
    0.70
    QLabel
    0.68
     TextView
    0.67
     UILabel
    0.62
     UIImageView
    0.59
     JLabel
    0.57
     UIButton
    0.57
    JLabel
    0.56
     ImageView
    0.56
    Activations Density 0.136%

    No Known Activations