© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 5995
    Prev
    Next
    INDEX
    Explanations

    affirmations of certainty or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.83
     OSI
    -0.73
     Jefus
    -0.72
    AccessFile
    -0.71
     Maren
    -0.71
    HtmlAttribute
    -0.70
    ^(@)
    -0.70
     AppColors
    -0.70
    WAP
    -0.70
    fiya
    -0.69
    POSITIVE LOGITS
     indeed
    3.41
    indeed
    2.99
     Indeed
    2.83
    Indeed
    2.80
     inderdaad
    1.79
    的确
    1.56
     infatti
    1.39
     effectivement
    1.36
    确实
    1.28
    確かに
    1.25
    Activations Density 0.071%

    No Known Activations