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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15430
    Prev
    Next
    INDEX
    Explanations

    references to significant events or actions related to justice and accountability

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

    Following "did" or "does"

    np_acts-logits-general · gemini-2.0-flash

    indeed affirmation or negation

    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
    hyrchwyd
    -0.58
    揄
    -0.57
    RegressionTest
    -0.56
     <>",
    -0.56
    هات
    -0.55
    ptid
    -0.55
     '\\;'
    -0.55
    Sólo
    -0.54
    BindView
    -0.54
    zymes
    -0.53
    POSITIVE LOGITS
     indeed
    1.44
    确实
    1.20
     inderdaad
    1.18
    的确
    1.18
    確實
    1.11
     effectivement
    1.11
    indeed
    1.09
     כן
    1.08
    Indeed
    1.03
    的確
    1.03
    Activations Density 0.386%

    No Known Activations