© 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. 5-GEMMASCOPE-RES-16K
    11. 6186
    Prev
    Next
    INDEX
    Explanations

    punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.98
    GEBURTSDATUM
    -0.98
     ModelExpression
    -0.98
    SharedDtor
    -0.88
    oa̍t
    -0.83
    Datuak
    -0.81
    IVEREF
    -0.79
     kaarangay
    -0.78
    UnsafeEnabled
    -0.78
     esternos
    -0.76
    POSITIVE LOGITS
    󠁢
    0.52
    tter
    0.47
     why
    0.47
    av
    0.46
    意思
    0.46
     but
    0.45
    iog
    0.45
     vė
    0.45
     unic
    0.45
    ้ม
    0.44
    Activations Density 0.011%

    No Known Activations