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. 2-GEMMASCOPE-RES-16K
    6. 6559
    Prev
    Next
    INDEX
    Explanations

    references to specific companies and their operations

    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
    ^(@)
    -0.32
     Efq
    -0.32
     Chriftian
    -0.31
    <h1>
    -0.31
    ✨:
    -0.31
     initWithFrame
    -0.30
     Majefty
    -0.30
    <h2>
    -0.30
      
    -0.29
     Shakspeare
    -0.29
    POSITIVE LOGITS
    <bos>
    0.97
    出版年
    0.36
    яза
    0.32
    multicolumn
    0.32
    ff
    0.32
    uitable
    0.30
    ρυ
    0.30
    нибудь
    0.30
     queſta
    0.30
     لينك
    0.29
    Activations Density 11.673%

    No Known Activations