© 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. 5860
    Prev
    Next
    INDEX
    Explanations

    instances of the word "describe" and its variants in contexts relating to detailed explanations or characterizations

    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
     Guel
    -0.68
    IBarButtonItem
    -0.67
    thenReturn
    -0.64
    djangoproject
    -0.61
    Amicalement
    -0.58
     zeker
    -0.58
     polyethylene
    -0.57
     impunity
    -0.56
     Toma
    -0.56
    Toma
    -0.56
    POSITIVE LOGITS
     describe
    1.77
     describes
    1.69
     describing
    1.68
     described
    1.67
     Describe
    1.54
    Describe
    1.52
     descri
    1.52
     DESCR
    1.50
     descriptions
    1.49
    described
    1.49
    Activations Density 0.160%

    No Known Activations