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. 5203
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or numerical data

    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
    mtd
    -0.50
    DataPropertyName
    -0.50
     then
    -0.44
    hér
    -0.42
    Flam
    -0.42
    WriteLiteral
    -0.40
     appear
    -0.39
     siis
    -0.39
    のこと
    -0.39
     completa
    -0.39
    POSITIVE LOGITS
     AssemblyCompany
    1.11
     Infórmanos
    1.03
    ousands
    0.99
     Theſe
    0.84
    SourceChecksum
    0.83
     $_"
    0.82
     IBRARY
    0.81
     estekak
    0.80
    ousand
    0.78
    ſelves
    0.77
    Activations Density 0.137%

    No Known Activations