© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9874
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their activities

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

    preceding "be" or "was"

    np_acts-logits-general · gemini-2.0-flash

    documentary details

    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
    olella
    -0.39
     DMCA
    -0.38
     Taschen
    -0.38
    워
    -0.37
    互
    -0.37
    PyExc
    -0.37
    epam
    -0.36
     mar
    -0.35
    면
    -0.35
    Saying
    -0.35
    POSITIVE LOGITS
    argout
    0.91
    +#+#
    0.85
    RTGC
    0.84
     estekak
    0.83
    الحياه
    0.83
    aarrggbb
    0.83
    thâu
    0.83
    PreferredItem
    0.82
    enumii
    0.81
    都是在
    0.80
    Activations Density 0.647%

    No Known Activations