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
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15585
    Prev
    Next
    INDEX
    Explanations

    numerical values related to time and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.78
    StoryboardSegue
    -0.60
    SequentialGroup
    -0.60
     ✭✭
    -0.60
    
    -0.59
    UnusedPrivate
    -0.57
    ViewImports
    -0.57
    awtextra
    -0.57
    XmlAccessorType
    -0.56
    EndProject
    -0.56
    POSITIVE LOGITS
     jį
    0.45
     siebie
    0.43
     hediye
    0.42
     Schauspieler
    0.41
     semula
    0.41
     enfermera
    0.40
     mercancías
    0.40
    fører
    0.40
    føl
    0.39
     opět
    0.39
    Activations Density 0.203%

    No Known Activations