© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8876
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "wan" and words related to quiz-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ligiloj
    -0.61
    лтамалар
    -0.51
    Хьажоргаш
    -0.50
    Искәрмәләр
    -0.45
     consultato
    -0.44
    astify
    -0.43
     Raoul
    -0.43
    analog
    -0.42
    /**
    -0.42
    mogorov
    -0.42
    POSITIVE LOGITS
    Renov
    0.60
    wan
    0.59
    Donnie
    0.56
     Goat
    0.55
    AddTagHelper
    0.54
     Donnie
    0.53
     CreateTagHelper
    0.53
     renamed
    0.52
     stain
    0.52
    Goat
    0.52
    Activations Density 0.409%

    No Known Activations