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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6682
    Prev
    Next
    INDEX
    Explanations

    instances of the word "adopt" and its variations, indicating a focus on the adoption of methods or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.65
     ujednoznacz
    -0.64
    elemField
    -0.59
    StringField
    -0.58
     ſei
    -0.58
    Хьажоргаш
    -0.58
    ServerError
    -0.58
     erſt
    -0.57
     חיצוניים
    -0.56
    
    -0.56
    POSITIVE LOGITS
     adopted
    2.13
     adoption
    2.02
     adopt
    1.99
    adopted
    1.84
     Adoption
    1.84
     adopting
    1.84
    adopt
    1.84
    Adoption
    1.79
     Adop
    1.78
     Adopted
    1.77
    Activations Density 0.150%

    No Known Activations