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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8470
    Prev
    Next
    INDEX
    Explanations

    rankings and positions in competitive sports contexts

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

    Rankings or positions

    np_acts-logits-general · gemini-2.0-flash

    ordinal ranking and position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.80
    webElementGuid
    -0.69
    ]--;
    -0.69
    Personensuche
    -0.67
    tvguidetime
    -0.63
    IUrlHelper
    -0.63
     []:
    -0.63
    ViewFeatures
    -0.63
     تضيفلها
    -0.62
     esternos
    -0.62
    POSITIVE LOGITS
     overall
    0.94
    overall
    0.86
     Overall
    0.67
    Overall
    0.65
     among
    0.65
    OVERALL
    0.63
     amongst
    0.61
     ranked
    0.61
     spot
    0.61
    among
    0.58
    Activations Density 0.123%

    No Known Activations