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. 12711
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or patterns involving the word "the"

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

    following the definite article "the"

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "in the"

    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
    SourceChecksum
    -0.72
    ElementException
    -0.60
    tagHelperRunner
    -0.59
    GeneratedValue
    -0.58
    ANTLR
    -0.54
    verwijspagina
    -0.54
    protoimpl
    -0.53
    printStackTrace
    -0.52
    ыгана
    -0.50
    URLEncoder
    -0.50
    POSITIVE LOGITS
     midst
    1.37
     meantime
    1.12
     absence
    1.10
     vicinity
    1.07
     wake
    1.01
     context
    0.99
     guise
    0.98
    absence
    0.93
     aftermath
    0.84
     vain
    0.84
    Activations Density 0.435%

    No Known Activations