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. 4-GEMMASCOPE-RES-16K
    6. 15817
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their related structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    extAlignment
    -0.82
    ParallelGroup
    -0.78
    NameInMap
    -0.77
    IntoConstraints
    -0.74
    expandindo
    -0.72
     مشين
    -0.69
    InputBorder
    -0.67
     nahilalakip
    -0.65
    ioutil
    -0.65
     AdapterView
    -0.62
    POSITIVE LOGITS
    (".")
    0.64
    ()]
    
    0.62
    .)}
    0.61
     credere
    0.57
    $.}
    0.56
     grama
    0.55
    .")
    0.55
    ()]);
    0.54
    "]
    0.53
    .”)
    0.53
    Activations Density 0.556%

    No Known Activations