Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6089
    Prev
    Next
    INDEX
    Explanations

    references to the concept of completeness or entirety

    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
    ../../
    -0.80
     shew
    -0.80
    shmi
    -0.77
    ha
    -0.72
    ciech
    -0.71
    <()>
    -0.69
    endphp
    -0.68
    poch
    -0.68
    confirmButton
    -0.66
    hyrchwyd
    -0.65
    POSITIVE LOGITS
    ์ตูน
    1.05
     Lacy
    1.02
     Egli
    0.92
    ſelf
    0.91
     myſelf
    0.88
     iſt
    0.87
     États
    0.84
     AMT
    0.84
    BeforeEach
    0.84
    Tires
    0.84
    Activations Density 0.052%

    No Known Activations