© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7727
    Prev
    Next
    INDEX
    Explanations

    references to reading or continuing content

    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
    IntoConstraints
    -0.61
    .*")]
    -0.60
    aneous
    -0.59
    ."</
    -0.56
    SequentialGroup
    -0.55
    writeField
    -0.54
    __':
    
    -0.54
    
    -0.51
    StoryboardSegue
    -0.51
    請繼續往下閱讀
    -0.50
    POSITIVE LOGITS
    ༘
    0.39
     ویکی‌پدی
    0.36
     ویکی‌آمباردا
    0.35
    parsedMessage
    0.34
    verifyException
    0.33
     ocasião
    0.32
     antigüedad
    0.32
    arraycopy
    0.32
     Isten
    0.31
    Pozdrawiam
    0.30
    Activations Density 0.255%

    No Known Activations