© 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. 16-GEMMASCOPE-RES-16K
    11. 14669
    Prev
    Next
    INDEX
    Explanations

    technical terms related to mechanical and electronic devices

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

    Follows a comma, often introducing examples

    np_acts-logits-general · gemini-2.0-flash

    lists ending in etc or and the like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.87
    GHIJKLM
    -0.85
     CURLOPT
    -0.83
     nahilalakip
    -0.82
     متعلقه
    -0.81
     AssemblyCompany
    -0.79
    mybatisplus
    -0.74
     TextAppearance
    -0.72
    OGND
    -0.71
     IBOutlet
    -0.71
    POSITIVE LOGITS
     other
    0.56
     linkovi
    0.47
     etc
    0.47
     any
    0.47
     similar
    0.46
     or
    0.43
    denk
    0.43
    ῦ
    0.42
     fellow
    0.41
    ixote
    0.40
    Activations Density 0.295%

    No Known Activations