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. 3-GEMMASCOPE-RES-16K
    6. 7605
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate conditions or states related to "that"

    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
    enumi
    -0.71
    addPreferredGap
    -0.54
     Trus
    -0.51
    پیوند
    -0.49
    ksy
    -0.48
    omation
    -0.47
    போ
    -0.47
     huyền
    -0.47
    Осно
    -0.47
    UDO
    -0.47
    POSITIVE LOGITS
    wherein
    0.78
     sodass
    0.77
    Geplaatst
    0.77
    Хьажоргаш
    0.73
     whereof
    0.70
     wherein
    0.69
    kubectl
    0.68
     înc
    0.67
     whereby
    0.64
     Jérusalem
    0.63
    Activations Density 0.279%

    No Known Activations