© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10834
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and contrasts between entities or concepts

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

    Word preceding "vs" or ":"

    np_acts-logits-general · gemini-2.0-flash

    ratios, comparisons, relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يكب
    -0.69
     invokingState
    -0.68
    AddTagHelper
    -0.68
    RegressionTest
    -0.66
    OGND
    -0.66
    OCCURRED
    -0.65
    ſelf
    -0.64
    ftagPool
    -0.59
     faſt
    -0.59
    tagHelperRunner
    -0.58
    POSITIVE LOGITS
    Cyfeiriadau
    0.44
     Din
    0.40
     nhau
    0.37
     rec
    0.36
    ⇄
    0.35
     tuk
    0.35
     its
    0.35
     manos
    0.35
    reuth
    0.34
    einander
    0.34
    Activations Density 1.362%

    No Known Activations