© 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 EvalsExportsinterp-engineNEWAPI 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. 2809
    Prev
    Next
    INDEX
    Explanations

    expressions of personal calling and purpose in life

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

    making a difference

    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
    RegressionTest
    -0.56
    évaluateur
    -0.55
    IntoConstraints
    -0.54
    Suspicious
    -0.53
    LookAnd
    -0.52
    DataMember
    -0.51
    $_['
    -0.50
    (!__
    -0.49
    ıştır
    -0.48
    wär
    -0.48
    POSITIVE LOGITS
     impact
    1.57
    impact
    1.37
     Impact
    1.37
    Impact
    1.35
     influence
    1.12
     impacts
    1.11
     impactful
    1.09
     impacting
    1.08
     IMPACT
    1.08
    IMPACT
    1.07
    Activations Density 0.117%

    No Known Activations