© 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. 15673
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate specialized or specific tasks and designs

    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
     Reſ
    -1.00
     iſt
    -0.99
     Efq
    -0.98
     itſelf
    -0.98
     Monfieur
    -0.97
    ſelf
    -0.93
     ―――――
    -0.90
     poffible
    -0.90
     Houſe
    -0.89
     myſelf
    -0.89
    POSITIVE LOGITS
     special
    1.46
     speciale
    1.26
    special
    1.24
    Special
    1.17
     especial
    1.15
     Special
    1.15
     khusus
    1.11
     spécial
    1.09
     specific
    1.08
    SPECIAL
    1.07
    Activations Density 0.328%

    No Known Activations