© 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. 14-GEMMASCOPE-RES-16K
    11. 15110
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions that indicate desire or intent related to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daudz
    -0.67
    baix
    -0.63
    ništvo
    -0.63
    FORMAN
    -0.59
    rinted
    -0.58
    えもん
    -0.57
     cobra
    -0.56
     Josephine
    -0.56
     Yaman
    -0.56
     athe
    -0.55
    POSITIVE LOGITS
     Wanna
    0.84
     estimés
    0.82
    ագրություններ
    0.79
    Wanna
    0.79
     wanna
    0.79
     be
    0.78
     gustaría
    0.77
     querem
    0.75
     bezeichneter
    0.73
    setupUi
    0.72
    Activations Density 0.120%

    No Known Activations