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. 11-GEMMASCOPE-RES-16K
    6. 14012
    Prev
    Next
    INDEX
    Explanations

    terms related to citizenship and residency status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.74
    ergies
    -0.69
     Trudeau
    -0.66
     ByteBuffer
    -0.66
     accru
    -0.66
    ButtonModule
    -0.66
    zzleHttp
    -0.65
     bif
    -0.64
    Higgs
    -0.64
     rubio
    -0.64
    POSITIVE LOGITS
     residents
    1.55
     resident
    1.55
     Residents
    1.52
     Resident
    1.39
    Residents
    1.39
    Resident
    1.25
    resident
    1.22
    residents
    1.18
     residing
    1.06
     residency
    1.05
    Activations Density 0.052%

    No Known Activations