© 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. 20-GEMMASCOPE-RES-16K
    11. 14675
    Prev
    Next
    INDEX
    Explanations

    references to card games, particularly board games and Gin Rummy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTLD
    -0.49
    BufferException
    -0.48
    WriteAttribute
    -0.48
    脚注の使い方
    -0.47
    #+#
    -0.47
    awtextra
    -0.47
    曖昧さ回避
    -0.44
    RepeatedField
    -0.43
    PyExc
    -0.42
    ьаж
    -0.42
    POSITIVE LOGITS
     informée
    0.56
    仕
    0.40
     насто
    0.39
     Administrativna
    0.39
     Laut
    0.38
    ONYMOUS
    0.38
    riu
    0.37
    getPort
    0.37
    ikor
    0.36
     ciutat
    0.36
    Activations Density 0.030%

    No Known Activations