© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 6852
    Prev
    Next
    INDEX
    Explanations

    repeated phrases and concepts relating to conditional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageOf
    -0.53
    TagMode
    -0.52
    RegressionTest
    -0.41
     BOL
    -0.41
     Bol
    -0.40
    windowFixed
    -0.40
     Carp
    -0.38
    뀔
    -0.37
     Prof
    -0.36
    Prof
    -0.35
    POSITIVE LOGITS
     disponibilités
    0.96
    MENAFN
    0.66
     nahilalakip
    0.65
     isNameExpr
    0.60
    出版年
    0.58
    isNameExpr
    0.56
    ंदीखरीदारी
    0.51
    oa̍t
    0.51
    pushFollow
    0.51
    verwijspagina
    0.47
    Activations Density 1.807%

    No Known Activations