© 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. 38-GEMMASCOPE-RES-16K
    6. 9746
    Prev
    Next
    INDEX
    Explanations

    terms and symbols related to broadcasting, media networks, and technical mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.68
    tagHelperRunner
    -0.66
    舺
    -0.61
    SequentialGroup
    -0.60
    JAXB
    -0.60
    LLocation
    -0.59
    IContainer
    -0.58
    Tembelea
    -0.56
     aze
    -0.56
     '\\;'
    -0.55
    POSITIVE LOGITS
     PeEnEo
    0.51
     informaciones
    0.40
     Erfolgs
    0.40
     Exteriores
    0.40
     Unterscheidung
    0.39
     matrícula
    0.39
     valsty
    0.38
     Verhältnisse
    0.38
     Constitucional
    0.38
     néz
    0.36
    Activations Density 1.750%

    No Known Activations