© 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. 3-GEMMASCOPE-RES-16K
    11. 5968
    Prev
    Next
    INDEX
    Explanations

    identifiers and property keys in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    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
    -0.71
    AnchorTagHelper
    -0.70
    براير
    -0.62
    Попис
    -0.60
    Demografia
    -0.58
    ايا
    -0.57
    PyExc
    -0.57
     Ler
    -0.57
    ípios
    -0.56
    ]}"
    -0.56
    POSITIVE LOGITS
    rungsseite
    0.81
    ंदीखरीदारी
    0.69
     enfans
    0.67
    SourceChecksum
    0.65
     uș
    0.64
     lucru
    0.64
     estimés
    0.64
     tarko
    0.60
    FieldDescriptor
    0.59
     barbati
    0.59
    Activations Density 0.118%

    No Known Activations