© 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. 7831
    Prev
    Next
    INDEX
    Explanations

    references to time scheduling and programming related to television broadcasts

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

    Tokens related to position or placement

    np_acts-logits-general · gemini-2.0-flash

    desired position

    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
    parsedMessage
    -0.82
    Diweddarwch
    -0.52
     informée
    -0.52
    
    -0.48
    onViewCreated
    -0.44
     AssemblyCompany
    -0.44
     HasFactory
    -0.43
     CreateTagHelper
    -0.43
    ɵɵelementStart
    -0.43
     GenerationType
    -0.43
    POSITIVE LOGITS
     location
    1.67
     placement
    1.51
     ubicación
    1.45
     위치
    1.42
    location
    1.41
    位置
    1.40
     locations
    1.39
     position
    1.34
     Location
    1.33
    的位置
    1.32
    Activations Density 0.820%

    No Known Activations