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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 1393
    Prev
    Next
    INDEX
    Explanations

    references to significant events and celebrations, particularly holidays and elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after holidays or special events

    np_acts-logits-general · gemini-2.0-flash

    election and holidays

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndInit
    -0.65
    .*")]
    -0.58
    OGND
    -0.56
    存于互联网档案馆
    -0.56
    GIVEREF
    -0.53
     lenker
    -0.52
    cshtml
    -0.52
    RenderAtEndOf
    -0.51
    Roles
    -0.48
    sigen
    -0.48
    POSITIVE LOGITS
     eve
    0.72
     day
    0.68
     Eve
    0.67
     Day
    0.66
    gift
    0.61
    day
    0.60
     morning
    0.59
     gift
    0.58
    eve
    0.58
     DAY
    0.57
    Activations Density 0.128%

    No Known Activations