© 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. 5880
    Prev
    Next
    INDEX
    Explanations

    information related to evidence and its interpretation within the context of arguments or discussions

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

    Punctuation followed by pronouns

    np_acts-logits-general · gemini-2.0-flash

    identifying "it" or "its"

    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
     Normdatei
    -0.65
     pinulongan
    -0.55
    webElementXpaths
    -0.54
     Signalez
    -0.53
    InstrumentedTest
    -0.52
    RegressionTest
    -0.50
    hyrchwyd
    -0.48
    PointerException
    -0.48
     informée
    -0.47
    Referencie
    -0.47
    POSITIVE LOGITS
     its
    2.02
     it
    2.00
     оно
    1.89
    它
    1.77
     Its
    1.66
     Оно
    1.63
    Its
    1.59
    它的
    1.53
     它
    1.38
    它是
    1.35
    Activations Density 2.366%

    No Known Activations