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. 8014
    Prev
    Next
    INDEX
    Explanations

    function and method definitions in code

    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
     propOrder
    -1.04
    ).</
    -0.86
    )";
    
    -0.85
    примеча
    -0.82
     Audiodateien
    -0.82
    BrowserModule
    -0.79
    Obrázky
    -0.78
     initComponents
    -0.74
     Pais
    -0.74
    Geplaatst
    -0.73
    POSITIVE LOGITS
    (__
    1.77
     (__
    1.67
     __
    1.65
     (!__
    1.45
    ->__
    1.45
    .__
    1.42
    &__
    1.35
    /__
    1.31
    #__
    1.27
    ("__
    1.27
    Activations Density 0.049%

    No Known Activations