© 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. 4324
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details related to electronic devices

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

    Operating systems and Linux distributions

    np_acts-logits-general · gemini-2.0-flash

    operating systems

    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
     betweenstory
    -0.52
     disambiguazione
    -0.52
     consultato
    -0.51
    oredCriteria
    -0.44
    Autoritní
    -0.42
     situe
    -0.37
    strijden
    -0.37
    #+#
    -0.37
    ManyToOne
    -0.36
    AnchorTagHelper
    -0.35
    POSITIVE LOGITS
     Linux
    1.12
     linux
    0.99
    Linux
    0.92
     OS
    0.88
     Windows
    0.88
    linux
    0.85
    操作系统
    0.84
     Ubuntu
    0.79
     Operating
    0.76
     operating
    0.75
    Activations Density 0.449%

    No Known Activations