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. 17-GEMMASCOPE-RES-16K
    6. 10726
    Prev
    Next
    INDEX
    Explanations

    references to historical events, particularly concerning the passage of time and changes in social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.77
     onOptions
    -0.69
    orteur
    -0.64
    SharedDtor
    -0.63
    cuit
    -0.62
    SharedCtor
    -0.62
    Rhestr
    -0.62
    ///</
    -0.61
    endphp
    -0.61
    |}{\
    -0.57
    POSITIVE LOGITS
     past
    0.90
     Vergangenheit
    0.85
    Past
    0.84
     Past
    0.82
    past
    0.76
     passé
    0.70
     memory
    0.70
     przesz
    0.69
    PAST
    0.67
     memories
    0.67
    Activations Density 0.152%

    No Known Activations