© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10479
    Prev
    Next
    INDEX
    Explanations

    elements related to managing identifiers or names in programming, especially focusing on strings and their characteristics

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

    Sentences starting with certain words

    np_acts-logits-general · gemini-2.0-flash

    starts with or begins with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     افتراض
    -0.48
    setzer
    -0.48
    SharedDtor
    -0.47
    zval
    -0.46
     }}}
    -0.43
     {},
    -0.43
    "]["
    -0.43
    (&:
    -0.42
    ContentValues
    -0.42
    vestream
    -0.41
    POSITIVE LOGITS
     starts
    1.57
     beginning
    1.55
     begins
    1.51
     starting
    1.47
     Starts
    1.44
     Begins
    1.42
    begins
    1.39
     Starting
    1.37
    Starting
    1.36
    beginning
    1.34
    Activations Density 0.422%

    No Known Activations