Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15020
    Prev
    Next
    INDEX
    Explanations

    references to fake news and misinformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InSection
    -0.85
    tamment
    -0.81
    urlpatterns
    -0.76
     Audiodateien
    -0.76
    grà
    -0.74
     vů
    -0.74
     volando
    -0.74
     LoginComponent
    -0.73
    BindingResult
    -0.73
    InkWell
    -0.72
    POSITIVE LOGITS
     fake
    1.37
     Fake
    1.26
    fake
    1.19
    Fake
    1.18
     fakes
    1.06
    FAKE
    0.95
     faux
    0.94
     Artificial
    0.92
     artificial
    0.92
     Faux
    0.91
    Activations Density 0.237%

    No Known Activations