© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5257
    Prev
    Next
    INDEX
    Explanations

    significant phrases or structures that suggest causation or explanation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    band
    -0.52
    ask
    -0.51
     bells
    -0.48
     contener
    -0.48
    __(/*!
    -0.47
     @
    -0.46
     require
    -0.45
    Ask
    -0.45
    ASK
    -0.45
     receb
    -0.45
    POSITIVE LOGITS
     Damit
    1.06
    Damit
    0.99
     Dadurch
    0.92
     waarmee
    0.87
     damit
    0.87
     Somit
    0.84
     thereby
    0.78
     womit
    0.78
    AsUp
    0.77
     dermed
    0.77
    Activations Density 0.236%

    No Known Activations