© 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. 22-GEMMASCOPE-RES-16K
    11. 8970
    Prev
    Next
    INDEX
    Explanations

    names and specifications of electronic devices, particularly related to Apple products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Apple and Samsung products

    np_acts-logits-general · gemini-2.0-flash

    product model series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.79
     ujednoznacz
    -0.76
     Baillargeon
    -0.75
    IsContent
    -0.72
     ModelExpression
    -0.71
     سكانية
    -0.70
     propOrder
    -0.67
    elemField
    -0.67
     >=",
    -0.64
    saraba
    -0.64
    POSITIVE LOGITS
     series
    0.69
     Pro
    0.69
     models
    0.67
     lineup
    0.62
     line
    0.59
     Series
    0.58
     generasi
    0.53
     pro
    0.53
     model
    0.52
     Models
    0.52
    Activations Density 0.161%

    No Known Activations