© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14983
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to rumors and speculation, especially in contexts involving public figures and decisions

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

    News reports and rumors

    np_acts-logits-general · gemini-2.0-flash

    reports and rumors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Reviewed
    -0.53
    InputTagHelper
    -0.51
    otide
    -0.45
    Gambas
    -0.44
    ofür
    -0.44
    createCanvas
    -0.43
     Reviewed
    -0.43
    SpringBootTest
    -0.42
    [:,:,
    -0.42
    HomeAsUpEnabled
    -0.42
    POSITIVE LOGITS
     reports
    2.25
     rumors
    2.09
     rumor
    2.01
     rumours
    1.98
     rumour
    1.93
     Reports
    1.90
    reports
    1.83
    Reports
    1.83
     report
    1.72
     reported
    1.71
    Activations Density 0.291%

    No Known Activations