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. 31-GEMMASCOPE-RES-16K
    6. 960
    Prev
    Next
    INDEX
    Explanations

    references to successful products and their features in comparative contexts

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

    words and phrases describing successful commercial products and their market performance.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.55
     BoxDecoration
    -0.54
    حوالہ
    -0.49
    otide
    -0.49
    lottesville
    -0.47
     mitten
    -0.47
     ControllerBase
    -0.46
    betical
    -0.45
     InputDecoration
    -0.44
     configureStore
    -0.43
    POSITIVE LOGITS
     with
    1.55
     using
    1.17
     With
    0.97
     dengan
    0.96
    With
    0.94
     avec
    0.94
     Using
    0.92
    Using
    0.91
    with
    0.88
     עם
    0.85
    Activations Density 1.066%

    No Known Activations