© 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. 3-GEMMASCOPE-RES-16K
    11. 911
    Prev
    Next
    INDEX
    Explanations

    references to relationships or connections between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Third
    -0.60
     phú
    -0.54
    i
    -0.53
     -
    -0.52
     avanti
    -0.51
    e
    -0.51
    摘
    -0.51
     something
    -0.50
     다
    -0.49
    o
    -0.48
    POSITIVE LOGITS
     whose
    2.33
    whose
    2.26
     Whose
    2.22
    Whose
    2.14
     whofe
    2.12
     whoſe
    2.07
     cuyas
    1.82
     cuya
    1.76
     cuyos
    1.76
     cuyo
    1.72
    Activations Density 0.029%

    No Known Activations