© 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. 2302
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that something is worth a visit or reading

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

    recommending reading books or versions

    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
    titleMargin
    -0.76
    StructEnd
    -0.72
    DrawerToggle
    -0.61
    ]=>
    -0.59
    ClientSize
    -0.58
    ochet
    -0.56
    CodedInputStream
    -0.55
     각
    -0.55
     måtte
    -0.55
    ごめん
    -0.54
    POSITIVE LOGITS
     almeno
    0.91
     definitely
    0.84
    Definitely
    0.83
     seriously
    0.78
    definitely
    0.76
     atleast
    0.74
     especially
    0.74
     IMHO
    0.73
    seriously
    0.71
     setidaknya
    0.71
    Activations Density 0.048%

    No Known Activations