© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 3997
    Prev
    Next
    INDEX
    Explanations

    references to "potyviruses."

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

    "Pot" followed by "entially/y"

    np_acts-logits-general · gemini-2.0-flash

    pot followed by y or entially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ROIT
    -0.60
    izioni
    -0.57
     touche
    -0.56
    didSet
    -0.55
     touché
    -0.54
    ollection
    -0.53
     Alexandra
    -0.52
    InstanceState
    -0.52
    Autowired
    -0.50
     сад
    -0.49
    POSITIVE LOGITS
    entially
    0.90
    ential
    0.83
    ency
    0.75
    ently
    0.74
    enced
    0.65
    ENCY
    0.64
    enti
    0.63
    encies
    0.61
    ring
    0.60
    ência
    0.58
    Activations Density 0.238%

    No Known Activations