© 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. 12-GEMMASCOPE-RES-16K
    6. 3188
    Prev
    Next
    INDEX
    Explanations

    elements related to dates and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.47
    Бахар
    -0.46
    BagConstraints
    -0.46
    CloseOperation
    -0.43
     الحره
    -0.43
     uLocal
    -0.40
    VideoCapture
    -0.39
    RenderAtEndOf
    -0.38
     تضيفلها
    -0.38
    ंदीखरीदारी
    -0.37
    POSITIVE LOGITS
    ValueStyle
    0.56
     ago
    0.49
     Gastgeber
    0.48
     begun
    0.46
     tarko
    0.46
     Lombardo
    0.45
     päät
    0.45
     rumours
    0.45
     unfore
    0.45
     rumors
    0.44
    Activations Density 0.841%

    No Known Activations