© 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. 10908
    Prev
    Next
    INDEX
    Explanations

    information related to consumer safety and quality assurance

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

    Comes before "is" or "the" (etc.)

    np_acts-logits-general · gemini-2.0-flash

    choosing or selecting

    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
    expandindo
    -0.60
     Efq
    -0.59
     PropertyChanged
    -0.58
    Portail
    -0.58
    ^(@)
    -0.57
     Wikisource
    -0.56
     TextAppearance
    -0.56
     pleaſure
    -0.56
    /$',
    -0.56
     Dage
    -0.54
    POSITIVE LOGITS
     choosing
    1.05
     selecting
    1.01
    選ぶ
    0.99
     Choosing
    0.98
     choose
    0.98
    Choosing
    0.97
     memilih
    0.97
     Pilih
    0.92
     scegliere
    0.92
    choosing
    0.92
    Activations Density 0.147%

    No Known Activations