© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    phrases that express comparison or contrast

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

    "As with"

    np_acts-logits-general · gemini-2.0-flash

    any followed by noun

    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
    StructEnd
    -0.81
    Diweddarwch
    -0.78
    บ้าง
    -0.64
     تانيه
    -0.63
     Normdatei
    -0.62
    ilités
    -0.61
     архивлан
    -0.60
    Enllaces
    -0.60
     للمعارف
    -0.59
     Efq
    -0.59
    POSITIVE LOGITS
     any
    2.61
    Any
    2.14
    any
    2.03
     Any
    2.01
     cualquier
    1.98
     qualquer
    1.97
    任何
    1.86
     anyone
    1.81
     ANY
    1.80
     любого
    1.75
    Activations Density 0.309%

    No Known Activations