© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7722
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with the concept of fake news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MLLoader
    -0.83
    +#+#
    -0.81
    OGND
    -0.80
    #+#
    -0.76
    ColumnHeaders
    -0.73
    SPATH
    -0.72
     vů
    -0.68
    ENOMEM
    -0.67
    amaño
    -0.67
     primaire
    -0.65
    POSITIVE LOGITS
     fake
    3.04
    fake
    2.74
     Fake
    2.70
    Fake
    2.61
     fakes
    2.28
     faked
    2.12
    FAKE
    2.11
     faking
    2.04
     faux
    1.93
     phony
    1.91
    Activations Density 0.192%

    No Known Activations