© 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. 13455
    Prev
    Next
    INDEX
    Explanations

    references to media coverage and press interactions

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

    the media or press

    np_acts-logits-general · gemini-2.0-flash

    media and press coverage

    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
     kaarangay
    -0.72
    ViewImports
    -0.70
    protoimpl
    -0.62
     للاسماء
    -0.58
    tableFuture
    -0.56
    Portail
    -0.56
    tagHelperRunner
    -0.55
    DockStyle
    -0.55
    exitRule
    -0.55
    ViewFeatures
    -0.54
    POSITIVE LOGITS
     media
    2.59
    media
    2.20
     press
    2.13
    Media
    2.08
     Media
    2.07
     MEDIA
    1.96
     journalists
    1.93
    MEDIA
    1.82
     reporters
    1.79
     presse
    1.73
    Activations Density 0.267%

    No Known Activations