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. 8-GEMMASCOPE-RES-16K
    6. 7629
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time and daily experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     par
    -0.44
    Famille
    -0.43
    rovna
    -0.43
    tså
    -0.42
     presidencia
    -0.42
     Extended
    -0.41
     extended
    -0.41
     LIRE
    -0.41
    moine
    -0.41
     vroe
    -0.41
    POSITIVE LOGITS
    AddTagHelper
    1.08
     increasingly
    0.86
    InvalidProtocol
    0.86
    Viited
    0.85
    QMetaType
    0.83
     Increasing
    0.83
    Increasing
    0.81
     increasing
    0.81
    越来越
    0.80
    increasing
    0.79
    Activations Density 0.178%

    No Known Activations