© 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. 4903
    Prev
    Next
    INDEX
    Explanations

    specific programming or technical terms and concepts related to software and data processing

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

    Options, such as command line arguments

    np_acts-logits-general · gemini-2.0-flash

    programming options and structure

    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
    -0.64
    HomeAsUpEnabled
    -0.61
    zeiti
    -0.60
     autorytatywna
    -0.56
    Rhestr
    -0.55
    AndEndTag
    -0.55
     دیکھیے
    -0.54
    Autoritní
    -0.54
     disparu
    -0.54
     religieuses
    -0.53
    POSITIVE LOGITS
     situation
    0.60
     situations
    0.58
    ymal
    0.57
     provisions
    0.57
     counterparts
    0.57
     categories
    0.57
     format
    0.56
     category
    0.56
     viewType
    0.55
     Direkt
    0.55
    Activations Density 0.921%

    No Known Activations