© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 7423
    Prev
    Next
    INDEX
    Explanations

    words indicating intent or action taken regarding a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -1.09
     d
    -0.97
     de
    -0.96
     her
    -0.95
     so
    -0.94
     du
    -0.94
     
    -0.93
     the
    -0.93
     C
    -0.91
     in
    -0.90
    POSITIVE LOGITS
     purpoſe
    1.85
     themſelves
    1.83
     Theſe
    1.82
     myſelf
    1.81
     Anſ
    1.79
     ſtate
    1.77
     ſche
    1.76
     Monfieur
    1.76
     Efq
    1.76
     Diſ
    1.74
    Activations Density 0.305%

    No Known Activations