© 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. 3-GEMMASCOPE-RES-16K
    6. 5818
    Prev
    Next
    INDEX
    Explanations

    references to the word "this" or its variations, indicating a focus on specificity and immediacy in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.53
     Norsk
    -0.53
     transférez
    -0.49
     Kebijakan
    -0.49
     dessa
    -0.48
    ništvo
    -0.47
    -------
    -0.47
    magem
    -0.47
     Populations
    -0.46
     Productos
    -0.45
    POSITIVE LOGITS
     este
    2.61
     Este
    2.47
    Este
    2.38
     ESTE
    1.89
     esta
    1.72
     Est
    1.69
    este
    1.60
    Est
    1.58
     EST
    1.50
     est
    1.41
    Activations Density 0.087%

    No Known Activations