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. 16-GEMMASCOPE-RES-16K
    6. 6231
    Prev
    Next
    INDEX
    Explanations

    words indicating complex relationships or conditions involving uncertainty, such as medical, scientific, or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.59
     BoxFit
    -0.57
    AddTagHelper
    -0.56
    DoubleQuotes
    -0.55
    ChildScrollView
    -0.54
    AsUp
    -0.52
    andExpect
    -0.50
    enumi
    -0.50
    ComponentModel
    -0.50
    <eos>
    -0.50
    POSITIVE LOGITS
    issauga
    0.80
    )");
    
    0.80
    })*/
    0.79
    };*/
    0.79
     quæ
    0.77
    ########.
    0.77
    ]";
    0.76
    脚注の使い方
    0.75
     $_"
    0.73
    Nuorodos
    0.73
    Activations Density 3.496%

    No Known Activations