© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10033
    Prev
    Next
    INDEX
    Explanations

    references to football teams and their performance in the context of playoffs and challenges

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

    NFC teams and the NFL playoffs

    np_acts-logits-general · gemini-2.0-flash

    NFC teams

    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
    SuspendLayout
    -0.48
    تفصیلات
    -0.46
     magasiner
    -0.45
    ukunft
    -0.45
    faden
    -0.44
    rungsseite
    -0.43
    MOUS
    -0.43
    Etimología
    -0.42
     végétale
    -0.42
    шое
    -0.42
    POSITIVE LOGITS
    NFC
    0.66
     NFC
    0.65
    itanie
    0.53
    Chham
    0.53
    random
    0.53
     Random
    0.52
    Random
    0.51
    rét
    0.51
     Giants
    0.50
    PYX
    0.49
    Activations Density 0.153%

    No Known Activations