Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 7110
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing quantity or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.56
    HLA
    -0.51
    DRS
    -0.50
     kierow
    -0.49
    oflavin
    -0.49
     laure
    -0.48
     Pesticides
    -0.47
    aita
    -0.47
    hydr
    -0.47
    ais
    -0.47
    POSITIVE LOGITS
     much
    0.94
     MUCH
    0.93
    much
    0.86
     Much
    0.84
    Much
    0.83
     more
    0.74
     mucho
    0.73
     little
    0.64
    Viel
    0.60
     mucha
    0.60
    Activations Density 0.060%

    No Known Activations