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. 14-GEMMASCOPE-RES-16K
    6. 2735
    Prev
    Next
    INDEX
    Explanations

    references to time periods, particularly years and their recurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.67
     /\.
    -0.63
     forKey
    -0.57
    findpost
    -0.56
     devriez
    -0.55
     FetchType
    -0.54
     LatLng
    -0.54
     Administrativna
    -0.53
    SequentialGroup
    -0.53
     /\.(
    -0.52
    POSITIVE LOGITS
     annual
    1.08
     annually
    0.97
     year
    0.95
     yearly
    0.93
    毎年
    0.91
    annual
    0.90
     biennial
    0.86
     Annual
    0.86
    Annual
    0.83
     année
    0.78
    Activations Density 0.245%

    No Known Activations