© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8219
    Prev
    Next
    INDEX
    Explanations

    patterns related to time or scheduling

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

    Hexadecimal representations and separators

    np_acts-logits-general · gemini-2.0-flash

    `key: value` structures

    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
     Reiz
    -0.41
    ]<=
    -0.38
     ویکی‌پدی
    -0.36
    An
    -0.36
    BE
    -0.35
    Set
    -0.35
    \_\_
    -0.34
    KY
    -0.34
    MT
    -0.34
    mName
    -0.34
    POSITIVE LOGITS
     للمعارف
    0.68
    StoryboardSegue
    0.66
    SequentialGroup
    0.65
    Datuak
    0.65
     lenker
    0.63
     EconPapers
    0.59
    Clik
    0.57
     Audiodateien
    0.56
    存于互联网档案馆
    0.56
     NSCoder
    0.54
    Activations Density 0.435%

    No Known Activations