© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12489
    Prev
    Next
    INDEX
    Explanations

    specific references to political figures and events

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

    DDT (likely referring to Donald Trump)

    np_acts-logits-general · gemini-2.0-flash

    DDT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.42
     Executive
    -0.37
    LayoutStyle
    -0.35
    ILE
    -0.35
     Start
    -0.33
    Ƚ
    -0.33
    ory
    -0.30
     Ill
    -0.30
    Typ
    -0.29
    Ill
    -0.28
    POSITIVE LOGITS
    MigrationBuilder
    0.69
    хьтан
    0.57
    تقاوى
    0.55
    #+#
    0.54
    舺
    0.54
     ivelany
    0.51
    Rujuakan
    0.50
    AppMethodBeat
    0.50
     automatiques
    0.50
     []:
    0.49
    Activations Density 0.579%

    No Known Activations