© 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. 4-GEMMASCOPE-RES-16K
    6. 1298
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to scoring or competitive outcomes, particularly ties in games or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.65
    ötzlich
    -0.64
    ļu
    -0.63
    McKin
    -0.63
    AccessorTable
    -0.62
     MessageBox
    -0.62
    mäß
    -0.61
    findpost
    -0.60
    ChildScrollView
    -0.59
    RegressionTest
    -0.59
    POSITIVE LOGITS
     tie
    2.58
     tied
    2.53
     ties
    2.49
     tying
    2.46
     Tie
    2.28
     Ties
    2.28
     Tied
    2.13
    Tie
    2.12
    Tied
    2.04
     TIE
    1.85
    Activations Density 0.065%

    No Known Activations