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. 3-GEMMASCOPE-RES-16K
    6. 5855
    Prev
    Next
    INDEX
    Explanations

    recurring use of the word "particularly" and similar terms indicating emphasis or specification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autoritní
    -0.88
     Houſe
    -0.69
     purpoſe
    -0.67
     houſe
    -0.64
    SharedDtor
    -0.63
     ainfi
    -0.63
    chränk
    -0.57
     pouvoit
    -0.56
     disambiguazione
    -0.56
    orithm
    -0.55
    POSITIVE LOGITS
     particularly
    3.58
     especially
    3.45
     Particularly
    3.22
    particularly
    3.16
    Especially
    3.08
     Especially
    3.08
    especially
    3.00
     especialmente
    2.95
     particularmente
    2.80
     особенно
    2.69
    Activations Density 0.116%

    No Known Activations