© 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. 34-GEMMASCOPE-RES-16K
    11. 11293
    Prev
    Next
    INDEX
    Explanations

    critical evaluations of arguments regarding various topics

    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
    不在
    -0.48
    不需要
    -0.41
    wußt
    -0.40
     unusually
    -0.39
    不受
    -0.38
    不用
    -0.37
    不存在
    -0.37
    Unusual
    -0.36
     Unusual
    -0.34
     ungewöhn
    -0.34
    POSITIVE LOGITS
     pales
    0.94
     insufficient
    0.92
     fails
    0.92
     inadequate
    0.88
    TagMode
    0.86
     misses
    0.82
     insufic
    0.79
     fail
    0.77
     inadequacy
    0.76
    だけでは
    0.75
    Activations Density 0.756%

    No Known Activations