© 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. 16175
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to ready-made or packaged goods and services

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

    Something is prepared or complete

    np_acts-logits-general · gemini-2.0-flash

    ready made

    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
    참고
    -0.51
    honneur
    -0.49
     alliés
    -0.46
     Numerade
    -0.46
    Lugares
    -0.46
    Personensuche
    -0.45
     ExecuteAsync
    -0.44
    曖昧さ回避
    -0.44
     pursu
    -0.43
    المشاركات
    -0.43
    POSITIVE LOGITS
     ready
    1.69
    ready
    1.51
     Ready
    1.46
    Ready
    1.38
     READY
    1.36
    READY
    1.24
     гото
    1.23
     prêt
    1.19
     prête
    1.08
     turnkey
    1.07
    Activations Density 0.239%

    No Known Activations