© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8037
    Prev
    Next
    INDEX
    Explanations

    Kotlin syntax elements related to functions and variable declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    发表于
    -0.58
    principalColumn
    -0.49
    NameInMap
    -0.48
    :✨
    -0.46
    WriteTagHelper
    -0.45
     disambiguazione
    -0.45
    TagMode
    -0.43
     ModelExpression
    -0.42
    estacks
    -0.42
     vectorielle
    -0.42
    POSITIVE LOGITS
    setVerticalGroup
    0.45
     several
    0.44
    GroupLayout
    0.44
    Cuándo
    0.43
    tagHelperRunner
    0.41
    Cuánt
    0.41
     record
    0.41
     ucz
    0.40
     Ann
    0.40
     Franz
    0.40
    Activations Density 0.070%

    No Known Activations