© 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. 2-GEMMASCOPE-RES-16K
    11. 4619
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or styles of doing things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unica
    -0.71
     nahilalakip
    -0.65
    까지
    -0.60
    riwal
    -0.59
    "]}
    -0.53
    brida
    -0.53
    にかけて
    -0.53
    SUCCESS
    -0.50
    roslav
    -0.50
    dsc
    -0.49
    POSITIVE LOGITS
     Quite
    0.73
     WAY
    0.72
     quite
    0.71
    Way
    0.70
    Quite
    0.70
    quite
    0.69
     ridiculously
    0.68
     awfully
    0.67
     numberWith
    0.66
     långt
    0.66
    Activations Density 0.166%

    No Known Activations