© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 3746
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and their associated values in code or structured data

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

    Comes before equation labels

    np_acts-logits-general · gemini-2.0-flash

    latex label commands

    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
    Portail
    -0.66
     }{@
    -0.64
    IndentedString
    -0.63
     مرئيه
    -0.62
    цездатний
    -0.60
     surla
    -0.54
     للاسماء
    -0.54
     autorytatywna
    -0.54
     referrerpolicy
    -0.53
    GOTREF
    -0.52
    POSITIVE LOGITS
    TabIndex
    1.41
     voorwaarden
    0.40
    enumi
    0.39
     AssemblyVersion
    0.38
    Билгалдахарш
    0.34
     chiave
    0.32
     vė
    0.32
     useStyles
    0.32
     consultato
    0.32
     volontà
    0.31
    Activations Density 0.047%

    No Known Activations