© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8065
    Prev
    Next
    INDEX
    Explanations

    phrases related to complex emotional or existential experiences

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

    Follows preposition "of" or "with"

    np_acts-logits-general · gemini-2.0-flash

    of/with followed by a noun/adjective

    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
    tagHelperRunner
    -0.54
    +#+#
    -0.52
    Rüyada
    -0.47
    BindingResult
    -0.43
    ValueStyle
    -0.43
     censiti
    -0.42
     AssemblyCompany
    -0.42
     rzeczy
    -0.41
    jsii
    -0.40
     naturelles
    -0.40
    POSITIVE LOGITS
    memoized
    0.40
     dedos
    0.40
    NonQuery
    0.39
    помним
    0.39
     otomatig
    0.39
    rawDesc
    0.39
    RTEE
    0.39
     Sä
    0.38
     neo
    0.38
    newArrayList
    0.38
    Activations Density 0.681%

    No Known Activations