© 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 - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12325
    Prev
    Next
    INDEX
    Explanations

    expressions of support and encouragement towards helping others

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

    "Helps," "hope," or "inspire" followed by a person

    np_acts-logits-general · gemini-2.0-flash

    helping many people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.57
    deauna
    -0.51
     entanto
    -0.49
    bindings
    -0.48
    iffa
    -0.47
     atve
    -0.47
    tlv
    -0.46
    isiert
    -0.45
    yní
    -0.45
    Gegen
    -0.45
    POSITIVE LOGITS
     many
    1.89
    many
    1.62
     muchos
    1.55
     millions
    1.55
     Many
    1.55
     thousands
    1.54
    Many
    1.52
     MANY
    1.46
    很多人
    1.44
     многих
    1.42
    Activations Density 0.420%

    No Known Activations