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. 2-GEMMASCOPE-RES-16K
    6. 1228
    Prev
    Next
    INDEX
    Explanations

    dates and numbers related to legal or administrative proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chữa
    -0.63
     réunis
    -0.62
     urmă
    -0.62
     arché
    -0.62
     tremp
    -0.62
     păr
    -0.61
    SHARE
    -0.60
    هما
    -0.60
     palsu
    -0.59
     raras
    -0.59
    POSITIVE LOGITS
    LookAnd
    1.03
    Personendaten
    0.91
     }}"></
    0.91
    parsedMessage
    0.88
     विश्वसनीयता
    0.86
     arşivlendi
    0.83
    fillType
    0.81
    migrationBuilder
    0.79
    ंदीखरीदारी
    0.76
    PyExc
    0.75
    Activations Density 0.366%

    No Known Activations