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. 14-GEMMASCOPE-RES-16K
    6. 258
    Prev
    Next
    INDEX
    Explanations

    items or products related to gifts and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GBIF
    -0.72
    +#+#
    -0.72
    %");
    -0.71
     استنادى
    -0.70
    RegressionTest
    -0.69
     дописавши
    -0.66
    }))
    
    -0.65
     محفوظة
    -0.65
    abancı
    -0.65
    setVerticalGroup
    -0.64
    POSITIVE LOGITS
    features
    0.46
    <eos>
    0.44
     
    0.43
     included
    0.43
    Features
    0.42
     features
    0.42
    tadır
    0.41
     sử
    0.41
     vem
    0.41
    Size
    0.41
    Activations Density 0.171%

    No Known Activations