© 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. 4-GEMMASCOPE-RES-16K
    11. 16071
    Prev
    Next
    INDEX
    Explanations

    instances of formal announcements or statements, particularly in press releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.53
    databind
    -0.51
    featureID
    -0.50
    ضات
    -0.47
    useNewUrlParser
    -0.46
    sess
    -0.43
    LORD
    -0.43
    řeba
    -0.43
     році
    -0.42
     Theodo
    -0.42
    POSITIVE LOGITS
    PRNewswire
    1.20
    
    0.86
     RELEASE
    0.86
     Release
    0.85
     comunicado
    0.84
     Releases
    0.82
    PRWEB
    0.81
     release
    0.81
     Announcement
    0.80
    RegistryLite
    0.79
    Activations Density 0.268%

    No Known Activations