© 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. 2-GEMMASCOPE-RES-16K
    11. 2385
    Prev
    Next
    INDEX
    Explanations

    words related to addresses and address handling

    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
    IsPostBack
    -0.73
     Lumpur
    -0.71
    }))
    -0.68
    jface
    -0.64
    สึก
    -0.64
    protoimpl
    -0.64
    hopal
    -0.63
    Carriera
    -0.63
    Tembelea
    -0.61
    ఔ
    -0.61
    POSITIVE LOGITS
    Address
    2.86
     Address
    2.72
    address
    2.61
     address
    2.42
     ADDRESS
    2.36
    ADDRESS
    2.27
     Addresses
    1.97
    getAddress
    1.91
     Adress
    1.85
     addresses
    1.85
    Activations Density 0.109%

    No Known Activations