© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30647
    Prev
    Next
    INDEX
    Explanations

    sections of text that indicate a deviation from normality or a comparison against a standard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    list, Comparator, quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uſed
    -0.69
     Efq
    -0.60
     ſch
    -0.59
    viewPager
    -0.58
    υχ
    -0.58
     CreateTagHelper
    -0.57
     سكانية
    -0.57
     ſeveral
    -0.57
     leſs
    -0.56
    ArgsConstructor
    -0.55
    POSITIVE LOGITS
    NameInMap
    0.60
    URLException
    0.56
    EndContext
    0.56
     racines
    0.51
     defaultstate
    0.50
    providedIn
    0.50
    rovna
    0.50
    ntag
    0.50
    ācija
    0.49
     nécessairement
    0.49
    Activations Density 0.146%

    No Known Activations