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. 15-GEMMASCOPE-RES-16K
    6. 8793
    Prev
    Next
    INDEX
    Explanations

    phrases that evaluate or analyze evidence and its presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    指定
    -0.53
    paz
    -0.50
    getCmp
    -0.48
    springframework
    -0.46
    лот
    -0.46
    barco
    -0.46
     指定
    -0.46
    Behavior
    -0.46
    measurement
    -0.44
    is
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    0.81
     pensée
    0.79
    ]")]
    0.75
     vérit
    0.74
    PerformLayout
    0.72
     pensées
    0.70
     Exacts
    0.69
    '],
    
    0.66
     saites
    0.65
    },{
    
    0.65
    Activations Density 0.710%

    No Known Activations