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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15694
    Prev
    Next
    INDEX
    Explanations

    references to screens and their attributes in the context of user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])):
    -0.88
    endphp
    -0.87
    "]));
    -0.82
     متعلقه
    -0.82
    ísimas
    -0.78
    ')));
    -0.77
     Justus
    -0.72
     propOrder
    -0.72
    خول
    -0.70
     cortas
    -0.70
    POSITIVE LOGITS
    Screen
    1.83
     SCREEN
    1.81
     Screen
    1.79
     screen
    1.72
     Screens
    1.70
     screens
    1.69
    SCREEN
    1.58
    Screens
    1.49
    screen
    1.45
    screens
    1.41
    Activations Density 0.040%

    No Known Activations