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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 161
    Prev
    Next
    INDEX
    Explanations

    formatted lists or enumerations within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onBackPressed
    -0.55
    CROSSTALK
    -0.55
    parseFrom
    -0.54
     esternos
    -0.54
    Majority
    -0.53
     torno
    -0.52
    makeConstraints
    -0.52
     Sol
    -0.51
    createdBy
    -0.51
    ouge
    -0.50
    POSITIVE LOGITS
     list
    1.88
     lists
    1.71
     liste
    1.53
     LIST
    1.52
     Lists
    1.50
     listing
    1.49
     List
    1.45
     lista
    1.42
     listed
    1.39
     Liste
    1.37
    Activations Density 0.115%

    No Known Activations