© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1756
    Prev
    Next
    INDEX
    Explanations

    terms related to significant mistakes or failures in contexts that involve geopolitical or economic implications

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

    failure or negative consequences

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    IntoConstraints
    -0.77
     tartalomajánló
    -0.72
    Παραπομπές
    -0.71
     doInBackground
    -0.67
     LoggerFactory
    -0.67
    tvguidetime
    -0.67
    Билгалдахарш
    -0.66
    dolu
    -0.64
     poveznice
    -0.63
     GenerationType
    -0.63
    POSITIVE LOGITS
     big
    1.27
     BIG
    1.13
    big
    1.12
    BIG
    1.09
     badly
    1.04
    Big
    0.86
     heavily
    0.82
     terribly
    0.82
     miserably
    0.81
     HUGE
    0.81
    Activations Density 0.128%

    No Known Activations