© 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. 10959
    Prev
    Next
    INDEX
    Explanations

    URLs and web-related content

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

    "Q" or "q"

    np_acts-logits-general · gemini-2.0-flash

    Q, q, Queen

    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
     ldc
    -0.55
    blom
    -0.49
     uſe
    -0.47
    しろ
    -0.45
     BorderSide
    -0.45
     Doğ
    -0.45
    toContain
    -0.45
     Bergh
    -0.43
    thmus
    -0.42
     Hul
    -0.42
    POSITIVE LOGITS
    Q
    1.24
     Q
    1.22
    q
    1.16
     Queen
    1.15
     q
    1.10
    Queen
    1.09
     queen
    1.05
     QUEEN
    1.03
    QB
    1.03
    queen
    1.02
    Activations Density 0.172%

    No Known Activations