© 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. 19-GEMMASCOPE-RES-16K
    11. 583
    Prev
    Next
    INDEX
    Explanations

    references to political claims and events, particularly surrounding elections and officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MonoBehaviour
    -0.69
     defaultstate
    -0.66
    UnitTesting
    -0.65
    createCanvas
    -0.63
     unknownFields
    -0.63
     المعيارى
    -0.60
    GEBURTSDATUM
    -0.59
     Signalez
    -0.58
     onCreateView
    -0.58
    UIControlState
    -0.58
    POSITIVE LOGITS
     previously
    1.23
     earlier
    1.06
     recently
    1.01
     Previously
    1.00
     sebelumnya
    1.00
    Previously
    0.96
    previously
    0.94
     later
    0.91
     hinted
    0.90
    Earlier
    0.90
    Activations Density 0.365%

    No Known Activations