© 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. 8553
    Prev
    Next
    INDEX
    Explanations

    numeric data, particularly counts and statistics related to participants in studies

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

    Numbers followed by "per" or "hundred"

    np_acts-logits-general · gemini-2.0-flash

    numbers and section markers

    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
    GEBURTS
    -0.60
    XmlAccessType
    -0.50
     nakalista
    -0.47
    nloa
    -0.42
    RTCK
    -0.41
    aimana
    -0.40
     sekali
    -0.39
    ftagPool
    -0.39
     CascadeType
    -0.38
     Inhalts
    -0.38
    POSITIVE LOGITS
     ब्रेकडाउन
    0.59
     EconPapers
    0.56
    BufferException
    0.52
     useAppContext
    0.50
    yntaxException
    0.47
    reactstrap
    0.46
    TintMode
    0.45
    AndEndTag
    0.43
     arşivlendi
    0.42
    peteer
    0.42
    Activations Density 0.322%

    No Known Activations