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. 11234
    Prev
    Next
    INDEX
    Explanations

    mathematical relations or connections in abstract contexts

    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
     BoxFit
    -1.06
     оригіналу
    -0.98
     UnityEditor
    -0.97
    
    -0.95
     Monfieur
    -0.94
    WebpackPlugin
    -0.91
    dubbo
    -0.90
     carbonic
    -0.89
    -------------</
    -0.89
    GOTREF
    -0.88
    POSITIVE LOGITS
     relations
    1.13
    relations
    1.01
     Relations
    0.97
    ob
    0.97
     relation
    0.94
     ob
    0.93
     RELATIONS
    0.91
     Ob
    0.85
    Relations
    0.83
    Ob
    0.77
    Activations Density 0.087%

    No Known Activations