© 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. 33-GEMMASCOPE-RES-16K
    11. 7449
    Prev
    Next
    INDEX
    Explanations

    technical terms and variables related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载附件
    -0.68
     utafitiHapana
    -0.66
    出版年
    -0.66
    GOTREF
    -0.61
    setVerticalGroup
    -0.60
     Taktlose
    -0.60
    StructEnd
    -0.59
    writeFieldEnd
    -0.59
    enterOuterAlt
    -0.58
    AndEndTag
    -0.58
    POSITIVE LOGITS
    L
    0.48
    f
    0.44
    F
    0.42
    Long
    0.35
    Color
    0.34
    float
    0.33
    TagHelper
    0.32
    th
    0.31
     بص
    0.30
    long
    0.30
    Activations Density 0.280%

    No Known Activations