© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 470
    Prev
    Next
    INDEX
    Explanations

    references to paired or coupled samples in a dataset

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

    "pair" or "pairs"

    np_acts-logits-general · gemini-2.0-flash

    pairs and paired items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     getContent
    -0.45
    /**
    -0.45
     ویکی‌پدی
    -0.44
     Rockefeller
    -0.41
    efeller
    -0.38
    róleo
    -0.38
    intellij
    -0.38
    abstractmethod
    -0.36
    Content
    -0.36
    deno
    -0.36
    POSITIVE LOGITS
     pair
    1.21
     Pair
    1.20
    Pair
    1.09
     pairs
    1.09
     paire
    1.08
    pair
    1.07
     paired
    1.06
     PAIR
    1.05
     pairing
    1.02
     Pairs
    1.01
    Activations Density 0.126%

    No Known Activations