© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 9243
    Prev
    Next
    INDEX
    Explanations

    phrases related to missing information or gaps in data

    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
    expandindo
    -0.72
     EconPapers
    -0.71
     noDo
    -0.70
     "..\..\..\
    -0.69
    PerformLayout
    -0.68
    RefNanny
    -0.65
     "..\..\
    -0.64
    ViewFeatures
    -0.62
    IUrlHelper
    -0.60
     <>",
    -0.59
    POSITIVE LOGITS
     is
    0.63
    CloseOperation
    0.60
    kheim
    0.57
     Baillargeon
    0.53
    Neko
    0.52
     prior
    0.52
     was
    0.50
     thing
    0.48
     goal
    0.48
     result
    0.48
    Activations Density 0.657%

    No Known Activations