© 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. 10-GEMMASCOPE-RES-16K
    11. 6897
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the primary role or significance of a factor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zelfs
    -0.68
     persino
    -0.62
    enni
    -0.59
     something
    -0.57
     jopa
    -0.54
    tagHelper
    -0.53
     addirittura
    -0.53
     qualsiasi
    -0.52
    X
    -0.52
     every
    -0.51
    POSITIVE LOGITS
     Mostly
    1.34
     Mainly
    1.33
    Mostly
    1.31
     Primarily
    1.30
     mainly
    1.26
     primarily
    1.26
    primarily
    1.23
     predominantly
    1.20
    mainly
    1.17
     mostly
    1.15
    Activations Density 0.325%

    No Known Activations