© 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. 34-GEMMASCOPE-RES-16K
    11. 10966
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in structured data representations or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -1.00
     autorytatywna
    -0.88
    expandindo
    -0.81
     للمعارف
    -0.81
     المعيارى
    -0.78
    $_['
    -0.77
    __*/
    -0.77
     EconPapers
    -0.75
     незавершена
    -0.73
     ſind
    -0.72
    POSITIVE LOGITS
    )
    0.96
    ()
    0.69
    }
    0.68
    ”
    0.65
    ]
    0.64
    "
    0.57
    ")
    0.50
    »
    0.49
    」
    0.46
    </
    0.44
    Activations Density 0.813%

    No Known Activations