Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 5970
    Prev
    Next
    INDEX
    Explanations

    temporal indicators or phrases signaling sequences of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finally
    -1.10
     eventually
    -0.97
    Finally
    -0.94
     Finally
    -0.93
    finally
    -0.93
     Finalmente
    -0.90
     gradually
    -0.89
     slowly
    -0.88
     ultimately
    -0.86
    eventually
    -0.85
    POSITIVE LOGITS
     thereafter
    1.05
     recognisable
    0.76
     afterwards
    0.76
     resourceCulture
    0.75
     recognizable
    0.74
    aneous
    0.73
     afterward
    0.69
     regretted
    0.66
     Thereafter
    0.65
    est
    0.65
    Activations Density 0.198%

    No Known Activations