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. 7-GEMMASCOPE-RES-16K
    6. 8827
    Prev
    Next
    INDEX
    Explanations

    references to specific names and entities, particularly related to historical figures and tribes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cree
    -0.77
    chaik
    -0.76
    Cree
    -0.75
     Moos
    -0.75
     Lovel
    -0.66
     year
    -0.66
     Dise
    -0.66
     Mee
    -0.65
     Booth
    -0.65
    знача
    -0.65
    POSITIVE LOGITS
    styleType
    1.03
    entile
    1.03
    NegativeButton
    1.03
     Gorg
    1.02
    IBOutlet
    1.00
    EndInit
    0.99
    HasForeignKey
    0.98
     שוליים
    0.97
     متعلقه
    0.96
    InputTagHelper
    0.95
    Activations Density 2.280%

    No Known Activations