Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7926
    Prev
    Next
    INDEX
    Explanations

    specific media formats and technologies related to computing and digital content

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

    Abbreviations/acronyms followed by other words

    np_acts-logits-general · gemini-2.0-flash

    technical abbreviations and acronyms

    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
    الحياه
    -0.71
    over
    -0.56
    ination
    -0.54
    انجليز
    -0.54
    ened
    -0.54
    ering
    -0.53
    ized
    -0.53
    esten
    -0.51
    ute
    -0.51
    rette
    -0.51
    POSITIVE LOGITS
     contextLoads
    0.54
     digitais
    0.50
     eletrônico
    0.48
     UITableViewCell
    0.47
    extré
    0.46
     térmica
    0.46
     grátis
    0.45
     morrer
    0.44
     financeira
    0.43
     inalámbrica
    0.43
    Activations Density 1.675%

    No Known Activations