© 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 EvalsExportsAPI 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. 3195
    Prev
    Next
    INDEX
    Explanations

    code-related terminology and structure

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

    Code using mocking or faking

    np_acts-logits-general · gemini-2.0-flash

    mocking methods in tests

    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
    devtool
    -0.26
     "..\..\
    -0.26
     desnuda
    -0.25
    autoload
    -0.25
    Rcpp
    -0.25
    parseFrom
    -0.24
     कोशिश
    -0.24
     sợi
    -0.23
     griega
    -0.23
     Tar
    -0.23
    POSITIVE LOGITS
     mock
    1.45
     Mock
    1.38
     faking
    1.34
     fake
    1.32
     Fake
    1.28
     faked
    1.27
    mock
    1.24
     pretended
    1.20
    Mock
    1.16
    Fake
    1.16
    Activations Density 0.235%

    No Known Activations