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. 2-GEMMASCOPE-RES-16K
    6. 6164
    Prev
    Next
    INDEX
    Explanations

    expressions related to function calls and mathematical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibouti
    -0.77
     complètes
    -0.72
    Materiál
    -0.71
     lunghezza
    -0.71
     prosjek
    -0.69
     lettura
    -0.69
    gensen
    -0.69
    ๊ะ
    -0.68
    etheless
    -0.66
    inghouse
    -0.66
    POSITIVE LOGITS
    }")
    
    0.71
    }],
    
    0.64
    rylic
    0.61
     yii
    0.61
    }]
    
    0.59
    SuppressMessage
    0.58
    RequestParam
    0.57
    getSystemService
    0.56
     Fernanda
    0.56
    nonatomic
    0.56
    Activations Density 0.337%

    No Known Activations