Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14883
    Prev
    Next
    INDEX
    Explanations

    instances of reported speech or quotations

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

    Comes before quotation marks and attribution

    np_acts-logits-general · gemini-2.0-flash

    reporting speech

    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
     EconPapers
    -0.89
     AssemblyCulture
    -0.87
    AddTagHelper
    -0.84
    })));
    -0.83
     transfieras
    -0.80
     Wiktionnaire
    -0.78
     '\\;'
    -0.76
    تقاوى
    -0.73
    rungsseite
    -0.73
     fieldNum
    -0.72
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.58
     referring
    0.51
     referencing
    0.51
    awtextra
    0.50
     telefónica
    0.47
     understanding
    0.46
     noting
    0.44
     față
    0.44
     simplifying
    0.42
    ाहरण
    0.42
    Activations Density 0.036%

    No Known Activations