© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1748
    Prev
    Next
    INDEX
    Explanations

    sections that include an introductory phrase or description about the authors or organization's background

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

    Text following the word "About"

    np_acts-logits-general · gemini-2.0-flash

    about the

    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
    AddTagHelper
    -0.89
     jadx
    -0.87
    CppMethod
    -0.85
    IsMutable
    -0.83
    WithIOException
    -0.83
    ")->
    -0.81
    ')],
    -0.80
    المشاركات
    -0.77
    )");
    
    -0.76
    országban
    -0.76
    POSITIVE LOGITS
     About
    0.63
    About
    0.60
     author
    0.54
     about
    0.52
    ABOUT
    0.51
     ABOUT
    0.51
     szerző
    0.50
     us
    0.48
     compañ
    0.48
     the
    0.47
    Activations Density 0.090%

    No Known Activations