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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 13318
    Prev
    Next
    INDEX
    Explanations

    the word "each" and variations of it, indicating a focus on inclusivity or consideration of individual components within a group

    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
     Marisa
    -0.50
     Arlene
    -0.49
    alarme
    -0.48
    laud
    -0.47
     Kalam
    -0.47
     Linton
    -0.47
     WMA
    -0.46
     Shand
    -0.46
     stifle
    -0.46
    ()">
    -0.46
    POSITIVE LOGITS
    Each
    1.00
     each
    0.99
     Each
    0.96
     EACH
    0.91
    each
    0.85
    EACH
    0.79
     Jedes
    0.76
    Ogni
    0.75
     Ogni
    0.73
     Chaque
    0.73
    Activations Density 0.067%

    No Known Activations