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. 5-GEMMASCOPE-RES-16K
    6. 4946
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to statistical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.93
     faſt
    -0.89
     itſelf
    -0.88
     Baillargeon
    -0.88
    ")));
    
    -0.83
     raiſ
    -0.83
    ()");
    -0.83
    ()]);
    -0.82
    '));
    
    -0.82
     ―――――
    -0.81
    POSITIVE LOGITS
     חיצוניים
    1.02
    protoimpl
    0.65
     跳转至
    0.61
     שוליים
    0.60
    enumi
    0.57
     HasFactory
    0.57
    GenerationType
    0.57
    <tbody>
    0.54
    Външни
    0.53
    InstrumentedTest
    0.52
    Activations Density 0.696%

    No Known Activations