© 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. 2489
    Prev
    Next
    INDEX
    Explanations

    statements expressing methods or approaches

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

    situation and its context

    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
    lineno
    -0.43
     صوتيه
    -0.42
    の中から
    -0.41
    вня
    -0.41
    LEn
    -0.40
     itself
    -0.40
     Leith
    -0.40
    あた
    -0.40
     ima
    -0.38
    await
    -0.38
    POSITIVE LOGITS
     situation
    1.08
    situation
    1.04
     Situation
    0.95
     SITUATION
    0.93
    Situation
    0.90
     situatie
    0.88
     situación
    0.83
     verhält
    0.81
     situa
    0.80
     situação
    0.77
    Activations Density 0.099%

    No Known Activations