© 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. 5-GEMMASCOPE-RES-16K
    11. 6309
    Prev
    Next
    INDEX
    Explanations

    references to keys and key-value pairs in data structures

    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
     Theſe
    -1.32
     ſeveral
    -1.30
     itſelf
    -1.28
     ―――――
    -1.26
     myſelf
    -1.26
     themſelves
    -1.25
     whoſe
    -1.23
     becauſe
    -1.22
     againſt
    -1.19
     $_"
    -1.17
    POSITIVE LOGITS
     keys
    2.08
    key
    1.95
     key
    1.90
     Keys
    1.81
     Key
    1.81
    keys
    1.79
    KEY
    1.77
     KEY
    1.73
    Key
    1.67
    Keys
    1.60
    Activations Density 0.044%

    No Known Activations