© 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. 1-GEMMASCOPE-RES-16K
    11. 3978
    Prev
    Next
    INDEX
    Explanations

    instances of the word "loose."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Carreira
    -0.68
    tonsoft
    -0.64
    脚注の使い方
    -0.61
     doInBackground
    -0.61
    RegressionTest
    -0.60
    JsonKey
    -0.60
    pyplot
    -0.59
    Hauptartikel
    -0.59
    selaer
    -0.58
     متعلقه
    -0.58
    POSITIVE LOGITS
     lose
    2.34
     loose
    1.92
    lose
    1.91
     losing
    1.91
    Lose
    1.87
     Lose
    1.77
     loses
    1.72
     loosing
    1.71
    loose
    1.62
    Loose
    1.60
    Activations Density 0.063%

    No Known Activations