© 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. 25-GEMMASCOPE-RES-16K
    11. 12622
    Prev
    Next
    INDEX
    Explanations

    references to organizations, roles, and structured entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doesn
    -0.69
     isn
    -0.68
    XmlAccessType
    -0.66
     says
    -0.66
     Says
    -0.64
     shouldn
    -0.60
     NSCoder
    -0.59
     seems
    -0.59
     means
    -0.58
     Isn
    -0.57
    POSITIVE LOGITS
     reviews
    0.76
     monitors
    0.75
     addresses
    0.72
     embar
    0.71
    reviews
    0.70
     coordinates
    0.69
     cons
    0.68
     guides
    0.64
    AddHtmlAttribute
    0.64
     implements
    0.63
    Activations Density 0.651%

    No Known Activations