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. 7-GEMMASCOPE-RES-16K
    6. 8826
    Prev
    Next
    INDEX
    Explanations

    phrases related to precision and measurement in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -1.47
     وتسجيلات
    -1.34
    出版年
    -1.29
    ^(@)
    -1.28
     nahilalakip
    -1.25
    bootstrapcdn
    -1.23
    Datuak
    -1.22
    NUMX
    -1.20
     NSCoder
    -1.17
     iſt
    -1.17
    POSITIVE LOGITS
    ↵↵
    1.27
    .
    0.99
    ↵
    0.97
    The
    0.81
    ↵↵↵
    0.77
     The
    0.76
    <eos>
    0.75
    I
    0.74
    1
    0.70
     
    0.70
    Activations Density 0.601%

    No Known Activations